diff --git a/README.md b/README.md
index d089d42c..d35ebe04 100644
--- a/README.md
+++ b/README.md
@@ -285,6 +285,7 @@ List of command-line flags
| `--no_use_cuda_fp16` | This can make models faster on some systems. |
| `--desc_act` | For models that don't have a quantize_config.json, this parameter is used to define whether to set desc_act or not in BaseQuantizeConfig. |
| `--disable_exllama` | Disable ExLlama kernel, which can improve inference speed on some systems. |
+| `--disable_exllamav2` | Disable ExLlamav2 kernel. |
#### GPTQ-for-LLaMa
diff --git a/docs/07 - Extensions.md b/docs/07 - Extensions.md
index 1d770ad2..78497888 100644
--- a/docs/07 - Extensions.md
+++ b/docs/07 - Extensions.md
@@ -18,7 +18,6 @@ If you create an extension, you are welcome to host it in a GitHub repository an
|[multimodal](https://github.com/oobabooga/text-generation-webui/tree/main/extensions/multimodal) | Adds multimodality support (text+images). For a detailed description see [README.md](https://github.com/oobabooga/text-generation-webui/tree/main/extensions/multimodal/README.md) in the extension directory. |
|[google_translate](https://github.com/oobabooga/text-generation-webui/tree/main/extensions/google_translate)| Automatically translates inputs and outputs using Google Translate.|
|[silero_tts](https://github.com/oobabooga/text-generation-webui/tree/main/extensions/silero_tts)| Text-to-speech extension using [Silero](https://github.com/snakers4/silero-models). When used in chat mode, responses are replaced with an audio widget. |
-|[elevenlabs_tts](https://github.com/oobabooga/text-generation-webui/tree/main/extensions/elevenlabs_tts)| Text-to-speech extension using the [ElevenLabs](https://beta.elevenlabs.io/) API. You need an API key to use it. |
|[whisper_stt](https://github.com/oobabooga/text-generation-webui/tree/main/extensions/whisper_stt)| Allows you to enter your inputs in chat mode using your microphone. |
|[sd_api_pictures](https://github.com/oobabooga/text-generation-webui/tree/main/extensions/sd_api_pictures)| Allows you to request pictures from the bot in chat mode, which will be generated using the AUTOMATIC1111 Stable Diffusion API. See examples [here](https://github.com/oobabooga/text-generation-webui/pull/309). |
|[character_bias](https://github.com/oobabooga/text-generation-webui/tree/main/extensions/character_bias)| Just a very simple example that adds a hidden string at the beginning of the bot's reply in chat mode. |
diff --git a/extensions/elevenlabs_tts/outputs/outputs-will-be-saved-here.txt b/extensions/elevenlabs_tts/outputs/outputs-will-be-saved-here.txt
deleted file mode 100644
index e69de29b..00000000
diff --git a/extensions/elevenlabs_tts/requirements.txt b/extensions/elevenlabs_tts/requirements.txt
deleted file mode 100644
index c3c0cc7e..00000000
--- a/extensions/elevenlabs_tts/requirements.txt
+++ /dev/null
@@ -1 +0,0 @@
-elevenlabs==0.2.24
diff --git a/extensions/elevenlabs_tts/script.py b/extensions/elevenlabs_tts/script.py
deleted file mode 100644
index af0c7458..00000000
--- a/extensions/elevenlabs_tts/script.py
+++ /dev/null
@@ -1,197 +0,0 @@
-import html
-import re
-from pathlib import Path
-
-import elevenlabs
-import gradio as gr
-
-from modules import chat, shared, ui_chat
-from modules.logging_colors import logger
-from modules.utils import gradio
-
-params = {
- 'activate': True,
- 'api_key': None,
- 'selected_voice': 'None',
- 'autoplay': False,
- 'show_text': True,
- 'model': 'eleven_monolingual_v1',
-}
-
-voices = None
-wav_idx = 0
-LANG_MODELS = ['eleven_monolingual_v1', 'eleven_multilingual_v1']
-
-
-def update_api_key(key):
- params['api_key'] = key
- if key is not None:
- elevenlabs.set_api_key(key)
-
-
-def refresh_voices():
- global params
- your_voices = elevenlabs.voices()
- voice_names = [voice.name for voice in your_voices]
- return voice_names
-
-
-def refresh_voices_dd():
- all_voices = refresh_voices()
- return gr.Dropdown.update(value=all_voices[0], choices=all_voices)
-
-
-def remove_tts_from_history(history):
- for i, entry in enumerate(history['internal']):
- history['visible'][i] = [history['visible'][i][0], entry[1]]
-
- return history
-
-
-def toggle_text_in_history(history):
- for i, entry in enumerate(history['visible']):
- visible_reply = entry[1]
- if visible_reply.startswith('\n\n{reply}"]
- else:
- history['visible'][i] = [history['visible'][i][0], f"{visible_reply.split('')[0]}"]
-
- return history
-
-
-def remove_surrounded_chars(string):
- # this expression matches to 'as few symbols as possible (0 upwards) between any asterisks' OR
- # 'as few symbols as possible (0 upwards) between an asterisk and the end of the string'
- return re.sub('\*[^\*]*?(\*|$)', '', string)
-
-
-def state_modifier(state):
- if not params['activate']:
- return state
-
- state['stream'] = False
- return state
-
-
-def input_modifier(string):
- if not params['activate']:
- return string
-
- shared.processing_message = "*Is recording a voice message...*"
- return string
-
-
-def history_modifier(history):
- # Remove autoplay from the last reply
- if len(history['internal']) > 0:
- history['visible'][-1] = [
- history['visible'][-1][0],
- history['visible'][-1][1].replace('controls autoplay>', 'controls>')
- ]
-
- return history
-
-
-def output_modifier(string):
- global params, wav_idx
-
- if not params['activate']:
- return string
-
- original_string = string
- string = remove_surrounded_chars(string)
- string = string.replace('"', '')
- string = string.replace('“', '')
- string = string.replace('\n', ' ')
- string = string.strip()
- if string == '':
- string = 'empty reply, try regenerating'
-
- output_file = Path(f'extensions/elevenlabs_tts/outputs/{wav_idx:06d}.mp3'.format(wav_idx))
- print(f'Outputting audio to {str(output_file)}')
- try:
- audio = elevenlabs.generate(text=html.unescape(string), voice=params['selected_voice'], model=params['model'])
- elevenlabs.save(audio, str(output_file))
-
- autoplay = 'autoplay' if params['autoplay'] else ''
- string = f''
- wav_idx += 1
- except elevenlabs.api.error.UnauthenticatedRateLimitError:
- string = "🤖 ElevenLabs Unauthenticated Rate Limit Reached - Please create an API key to continue\n\n"
- except elevenlabs.api.error.RateLimitError:
- string = "🤖 ElevenLabs API Tier Limit Reached\n\n"
- except elevenlabs.api.error.APIError as err:
- string = f"🤖 ElevenLabs Error: {err}\n\n"
-
- if params['show_text']:
- string += f'\n\n{original_string}'
-
- shared.processing_message = "*Is typing...*"
- return string
-
-
-def ui():
- global voices
- if not voices:
- voices = refresh_voices()
- selected = params['selected_voice']
- if selected == 'None':
- params['selected_voice'] = voices[0]
- elif selected not in voices:
- logger.error(f'Selected voice {selected} not available, switching to {voices[0]}')
- params['selected_voice'] = voices[0]
-
- # Gradio elements
- with gr.Row():
- activate = gr.Checkbox(value=params['activate'], label='Activate TTS')
- autoplay = gr.Checkbox(value=params['autoplay'], label='Play TTS automatically')
- show_text = gr.Checkbox(value=params['show_text'], label='Show message text under audio player')
-
- with gr.Row():
- voice = gr.Dropdown(value=params['selected_voice'], choices=voices, label='TTS Voice')
- refresh = gr.Button(value='Refresh')
-
- with gr.Row():
- if params['api_key']:
- api_key = gr.Textbox(value=params['api_key'], label='API Key')
- update_api_key(params['api_key'])
- else:
- api_key = gr.Textbox(placeholder="Enter your API key.", label='API Key')
-
- with gr.Row():
- model = gr.Dropdown(value=params['model'], choices=LANG_MODELS, label='Language model')
-
- with gr.Row():
- convert = gr.Button('Permanently replace audios with the message texts')
- convert_cancel = gr.Button('Cancel', visible=False)
- convert_confirm = gr.Button('Confirm (cannot be undone)', variant="stop", visible=False)
-
- # Convert history with confirmation
- convert_arr = [convert_confirm, convert, convert_cancel]
- convert.click(lambda: [gr.update(visible=True), gr.update(visible=False), gr.update(visible=True)], None, convert_arr)
- convert_confirm.click(
- lambda: [gr.update(visible=False), gr.update(visible=True), gr.update(visible=False)], None, convert_arr).then(
- remove_tts_from_history, gradio('history'), gradio('history')).then(
- chat.save_history, gradio('history', 'unique_id', 'character_menu', 'mode'), None).then(
- chat.redraw_html, gradio(ui_chat.reload_arr), gradio('display'))
-
- convert_cancel.click(lambda: [gr.update(visible=False), gr.update(visible=True), gr.update(visible=False)], None, convert_arr)
-
- # Toggle message text in history
- show_text.change(
- lambda x: params.update({"show_text": x}), show_text, None).then(
- toggle_text_in_history, gradio('history'), gradio('history')).then(
- chat.save_history, gradio('history', 'unique_id', 'character_menu', 'mode'), None).then(
- chat.redraw_html, gradio(ui_chat.reload_arr), gradio('display'))
-
- # Event functions to update the parameters in the backend
- activate.change(lambda x: params.update({'activate': x}), activate, None)
- voice.change(lambda x: params.update({'selected_voice': x}), voice, None)
- api_key.change(update_api_key, api_key, None)
- model.change(lambda x: params.update({'model': x}), model, None)
- # connect.click(check_valid_api, [], connection_status)
- refresh.click(refresh_voices_dd, [], voice)
- # Event functions to update the parameters in the backend
- autoplay.change(lambda x: params.update({"autoplay": x}), autoplay, None)
diff --git a/extensions/openai/logits.py b/extensions/openai/logits.py
index 9d2fe41c..357e70fa 100644
--- a/extensions/openai/logits.py
+++ b/extensions/openai/logits.py
@@ -8,4 +8,4 @@ def _get_next_logits(body):
state = process_parameters(body) if use_samplers else {}
state['stream'] = True
- return get_next_logits(body['prompt'], state, use_samplers, "", return_dict=True)
+ return get_next_logits(body['prompt'], state, use_samplers, "", top_logits=body['top_logits'], return_dict=True)
diff --git a/extensions/openai/typing.py b/extensions/openai/typing.py
index 47ddd789..3a212dd9 100644
--- a/extensions/openai/typing.py
+++ b/extensions/openai/typing.py
@@ -1,6 +1,6 @@
import json
import time
-from typing import List
+from typing import Dict, List
from pydantic import BaseModel, Field
@@ -120,7 +120,7 @@ class ChatCompletionResponse(BaseModel):
class EmbeddingsRequest(BaseModel):
- input: str | List[str]
+ input: str | List[str] | List[int] | List[List[int]]
model: str | None = Field(default=None, description="Unused parameter. To change the model, set the OPENEDAI_EMBEDDING_MODEL and OPENEDAI_EMBEDDING_DEVICE environment variables before starting the server.")
encoding_format: str = Field(default="float", description="Can be float or base64.")
user: str | None = Field(default=None, description="Unused parameter.")
@@ -156,6 +156,7 @@ class TokenCountResponse(BaseModel):
class LogitsRequestParams(BaseModel):
prompt: str
use_samplers: bool = False
+ top_logits: int | None = 50
frequency_penalty: float | None = 0
max_tokens: int | None = 16
presence_penalty: float | None = 0
@@ -168,7 +169,7 @@ class LogitsRequest(GenerationOptions, LogitsRequestParams):
class LogitsResponse(BaseModel):
- logits: dict
+ logits: Dict[str, float]
class ModelInfoResponse(BaseModel):
diff --git a/extensions/whisper_stt/requirements.txt b/extensions/whisper_stt/requirements.txt
index b650f6b6..576c955f 100644
--- a/extensions/whisper_stt/requirements.txt
+++ b/extensions/whisper_stt/requirements.txt
@@ -1,4 +1,4 @@
SpeechRecognition==3.10.0
-git+https://github.com/oobabooga/whisper.git
+openai-whisper
soundfile
ffmpeg
diff --git a/instruction-templates/Mistral.yaml b/instruction-templates/Mistral.yaml
index 785a3a32..0b6baf11 100644
--- a/instruction-templates/Mistral.yaml
+++ b/instruction-templates/Mistral.yaml
@@ -1,16 +1,7 @@
instruction_template: |-
- {%- set found_item = false -%}
- {%- for message in messages -%}
- {%- if message['role'] == 'system' -%}
- {%- set found_item = true -%}
- {%- endif -%}
- {%- endfor -%}
- {%- if not found_item -%}
- {{- '' + '' + '' -}}
- {%- endif %}
{%- for message in messages %}
{%- if message['role'] == 'system' -%}
- {{- '' + message['content'] + '' -}}
+ {{- message['content'] -}}
{%- else -%}
{%- if message['role'] == 'user' -%}
{{-'[INST] ' + message['content'] + ' [/INST]'-}}
diff --git a/models/config.yaml b/models/config.yaml
index f18687ae..197d4b35 100644
--- a/models/config.yaml
+++ b/models/config.yaml
@@ -174,7 +174,7 @@
instruction_template: 'OpenChat'
.*codellama.*instruct:
instruction_template: 'Llama-v2'
-.*mistral.*instruct:
+.*(mistral|mixtral).*instruct:
instruction_template: 'Mistral'
.*mistral.*openorca:
instruction_template: 'ChatML'
diff --git a/modules/AutoGPTQ_loader.py b/modules/AutoGPTQ_loader.py
index f33803e8..514a6ee5 100644
--- a/modules/AutoGPTQ_loader.py
+++ b/modules/AutoGPTQ_loader.py
@@ -52,6 +52,7 @@ def load_quantized(model_name):
'quantize_config': quantize_config,
'use_cuda_fp16': not shared.args.no_use_cuda_fp16,
'disable_exllama': shared.args.disable_exllama,
+ 'disable_exllamav2': shared.args.disable_exllamav2,
}
logger.info(f"The AutoGPTQ params are: {params}")
diff --git a/modules/chat.py b/modules/chat.py
index ab0d70a9..7a44c03e 100644
--- a/modules/chat.py
+++ b/modules/chat.py
@@ -215,40 +215,47 @@ def chatbot_wrapper(text, state, regenerate=False, _continue=False, loading_mess
yield output
return
- just_started = True
visible_text = None
stopping_strings = get_stopping_strings(state)
is_stream = state['stream']
# Prepare the input
- if not any((regenerate, _continue)):
+ if not (regenerate or _continue):
visible_text = html.escape(text)
# Apply extensions
text, visible_text = apply_extensions('chat_input', text, visible_text, state)
text = apply_extensions('input', text, state, is_chat=True)
+ output['internal'].append([text, ''])
+ output['visible'].append([visible_text, ''])
+
# *Is typing...*
if loading_message:
- yield {'visible': output['visible'] + [[visible_text, shared.processing_message]], 'internal': output['internal']}
+ yield {
+ 'visible': output['visible'][:-1] + [[output['visible'][-1][0], shared.processing_message]],
+ 'internal': output['internal']
+ }
else:
text, visible_text = output['internal'][-1][0], output['visible'][-1][0]
if regenerate:
- output['visible'].pop()
- output['internal'].pop()
-
- # *Is typing...*
if loading_message:
- yield {'visible': output['visible'] + [[visible_text, shared.processing_message]], 'internal': output['internal']}
+ yield {
+ 'visible': output['visible'][:-1] + [[visible_text, shared.processing_message]],
+ 'internal': output['internal'][:-1] + [[text, '']]
+ }
elif _continue:
last_reply = [output['internal'][-1][1], output['visible'][-1][1]]
if loading_message:
- yield {'visible': output['visible'][:-1] + [[visible_text, last_reply[1] + '...']], 'internal': output['internal']}
+ yield {
+ 'visible': output['visible'][:-1] + [[visible_text, last_reply[1] + '...']],
+ 'internal': output['internal']
+ }
# Generate the prompt
kwargs = {
'_continue': _continue,
- 'history': output,
+ 'history': output if _continue else {k: v[:-1] for k, v in output.items()}
}
prompt = apply_extensions('custom_generate_chat_prompt', text, state, **kwargs)
if prompt is None:
@@ -270,12 +277,6 @@ def chatbot_wrapper(text, state, regenerate=False, _continue=False, loading_mess
yield output
return
- if just_started:
- just_started = False
- if not _continue:
- output['internal'].append(['', ''])
- output['visible'].append(['', ''])
-
if _continue:
output['internal'][-1] = [text, last_reply[0] + reply]
output['visible'][-1] = [visible_text, last_reply[1] + visible_reply]
diff --git a/modules/loaders.py b/modules/loaders.py
index d1f8343f..c7e7653e 100644
--- a/modules/loaders.py
+++ b/modules/loaders.py
@@ -25,6 +25,7 @@ loaders_and_params = OrderedDict({
'rope_freq_base',
'compress_pos_emb',
'disable_exllama',
+ 'disable_exllamav2',
'transformers_info'
],
'llama.cpp': [
@@ -94,6 +95,7 @@ loaders_and_params = OrderedDict({
'groupsize',
'desc_act',
'disable_exllama',
+ 'disable_exllamav2',
'gpu_memory',
'cpu_memory',
'cpu',
diff --git a/modules/logits.py b/modules/logits.py
index 5d0d3210..e12cf6e7 100644
--- a/modules/logits.py
+++ b/modules/logits.py
@@ -8,7 +8,7 @@ from modules.text_generation import generate_reply
global_scores = None
-def get_next_logits(prompt, state, use_samplers, previous, return_dict=False):
+def get_next_logits(prompt, state, use_samplers, previous, top_logits=50, return_dict=False):
if shared.model is None:
logger.error("No model is loaded! Select one in the Model tab.")
return 'Error: No model is loaded1 Select one in the Model tab.', previous
@@ -50,8 +50,7 @@ def get_next_logits(prompt, state, use_samplers, previous, return_dict=False):
scores = output['logits'][-1][-1]
probs = torch.softmax(scores, dim=-1, dtype=torch.float)
- topk_values, topk_indices = torch.topk(probs, k=50, largest=True, sorted=True)
- topk_values = [f"{float(i):.5f}" for i in topk_values]
+ topk_values, topk_indices = torch.topk(probs, k=top_logits, largest=True, sorted=True)
if is_non_hf_exllamav1 or is_non_hf_llamacpp:
topk_indices = [i.expand((1, 1)) for i in topk_indices]
@@ -61,12 +60,14 @@ def get_next_logits(prompt, state, use_samplers, previous, return_dict=False):
tokens = [shared.tokenizer.decode(i) for i in topk_indices]
if return_dict:
+ topk_values = [float(i) for i in topk_values]
output = {}
for row in list(zip(topk_values, tokens)):
output[row[1]] = row[0]
return output
else:
+ topk_values = [f"{float(i):.5f}" for i in topk_values]
output = ''
for row in list(zip(topk_values, tokens)):
output += f"{row[0]} - {repr(row[1])}\n"
diff --git a/modules/models.py b/modules/models.py
index f77fc941..49e5f818 100644
--- a/modules/models.py
+++ b/modules/models.py
@@ -156,7 +156,7 @@ def huggingface_loader(model_name):
LoaderClass = AutoModelForCausalLM
# Load the model in simple 16-bit mode by default
- if not any([shared.args.cpu, shared.args.load_in_8bit, shared.args.load_in_4bit, shared.args.auto_devices, shared.args.disk, shared.args.deepspeed, shared.args.gpu_memory is not None, shared.args.cpu_memory is not None, shared.args.compress_pos_emb > 1, shared.args.alpha_value > 1, shared.args.disable_exllama]):
+ if not any([shared.args.cpu, shared.args.load_in_8bit, shared.args.load_in_4bit, shared.args.auto_devices, shared.args.disk, shared.args.deepspeed, shared.args.gpu_memory is not None, shared.args.cpu_memory is not None, shared.args.compress_pos_emb > 1, shared.args.alpha_value > 1, shared.args.disable_exllama, shared.args.disable_exllamav2]):
model = LoaderClass.from_pretrained(path_to_model, **params)
if torch.backends.mps.is_available():
device = torch.device('mps')
@@ -221,11 +221,16 @@ def huggingface_loader(model_name):
if shared.args.disk:
params['offload_folder'] = shared.args.disk_cache_dir
- if shared.args.disable_exllama:
+ if shared.args.disable_exllama or shared.args.disable_exllamav2:
try:
- gptq_config = GPTQConfig(bits=config.quantization_config.get('bits', 4), disable_exllama=True)
+ gptq_config = GPTQConfig(
+ bits=config.quantization_config.get('bits', 4),
+ disable_exllama=shared.args.disable_exllama,
+ disable_exllamav2=shared.args.disable_exllamav2,
+ )
+
params['quantization_config'] = gptq_config
- logger.info('Loading with ExLlama kernel disabled.')
+ logger.info(f'Loading with disable_exllama={shared.args.disable_exllama} and disable_exllamav2={shared.args.disable_exllamav2}.')
except:
exc = traceback.format_exc()
logger.error('Failed to disable exllama. Does the config.json for this model contain the necessary quantization info?')
diff --git a/modules/shared.py b/modules/shared.py
index b0888935..adebe62d 100644
--- a/modules/shared.py
+++ b/modules/shared.py
@@ -133,6 +133,7 @@ parser.add_argument('--no_inject_fused_mlp', action='store_true', help='Triton m
parser.add_argument('--no_use_cuda_fp16', action='store_true', help='This can make models faster on some systems.')
parser.add_argument('--desc_act', action='store_true', help='For models that do not have a quantize_config.json, this parameter is used to define whether to set desc_act or not in BaseQuantizeConfig.')
parser.add_argument('--disable_exllama', action='store_true', help='Disable ExLlama kernel, which can improve inference speed on some systems.')
+parser.add_argument('--disable_exllamav2', action='store_true', help='Disable ExLlamav2 kernel.')
# GPTQ-for-LLaMa
parser.add_argument('--wbits', type=int, default=0, help='Load a pre-quantized model with specified precision in bits. 2, 3, 4 and 8 are supported.')
diff --git a/modules/ui.py b/modules/ui.py
index 45849fe3..8bfc9491 100644
--- a/modules/ui.py
+++ b/modules/ui.py
@@ -70,6 +70,7 @@ def list_model_elements():
'no_inject_fused_mlp',
'no_use_cuda_fp16',
'disable_exllama',
+ 'disable_exllamav2',
'cfg_cache',
'no_flash_attn',
'cache_8bit',
diff --git a/modules/ui_model_menu.py b/modules/ui_model_menu.py
index 7b6767dc..7242d117 100644
--- a/modules/ui_model_menu.py
+++ b/modules/ui_model_menu.py
@@ -125,6 +125,7 @@ def create_ui():
shared.gradio['logits_all'] = gr.Checkbox(label="logits_all", value=shared.args.logits_all, info='Needs to be set for perplexity evaluation to work. Otherwise, ignore it, as it makes prompt processing slower.')
shared.gradio['use_flash_attention_2'] = gr.Checkbox(label="use_flash_attention_2", value=shared.args.use_flash_attention_2, info='Set use_flash_attention_2=True while loading the model.')
shared.gradio['disable_exllama'] = gr.Checkbox(label="disable_exllama", value=shared.args.disable_exllama, info='Disable ExLlama kernel.')
+ shared.gradio['disable_exllamav2'] = gr.Checkbox(label="disable_exllamav2", value=shared.args.disable_exllamav2, info='Disable ExLlamav2 kernel.')
shared.gradio['no_flash_attn'] = gr.Checkbox(label="no_flash_attn", value=shared.args.no_flash_attn, info='Force flash-attention to not be used.')
shared.gradio['cache_8bit'] = gr.Checkbox(label="cache_8bit", value=shared.args.cache_8bit, info='Use 8-bit cache to save VRAM.')
shared.gradio['no_use_fast'] = gr.Checkbox(label="no_use_fast", value=shared.args.no_use_fast, info='Set use_fast=False while loading the tokenizer.')
diff --git a/one_click.py b/one_click.py
index 7e2cf7e8..76e8580e 100644
--- a/one_click.py
+++ b/one_click.py
@@ -218,7 +218,7 @@ def install_webui():
elif is_linux() and (choice == "C" or choice == "N"):
install_pytorch = "python -m pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cpu"
elif choice == "D":
- install_pytorch = "python -m pip install torch==2.0.1a0 torchvision==0.15.2a0 intel_extension_for_pytorch==2.0.110+xpu --extra-index-url https://pytorch-extension.intel.com/release-whl/stable/xpu/us/"
+ install_pytorch = "python -m pip install torch==2.1.0a0 torchvision==0.16.0a0 intel_extension_for_pytorch==2.1.10+xpu --extra-index-url https://pytorch-extension.intel.com/release-whl/stable/xpu/us/"
# Install Git and then Pytorch
print_big_message("Installing PyTorch.")
diff --git a/requirements.txt b/requirements.txt
index aedf9d40..8e3f09cd 100644
--- a/requirements.txt
+++ b/requirements.txt
@@ -27,24 +27,24 @@ bitsandbytes==0.41.1; platform_system != "Windows"
https://github.com/jllllll/bitsandbytes-windows-webui/releases/download/wheels/bitsandbytes-0.41.1-py3-none-win_amd64.whl; platform_system == "Windows"
# llama-cpp-python (CPU only, AVX2)
-https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.23+cpuavx2-cp311-cp311-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
-https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.23+cpuavx2-cp310-cp310-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
-https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.23+cpuavx2-cp39-cp39-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.9"
-https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.23+cpuavx2-cp38-cp38-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.8"
-https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.23+cpuavx2-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
-https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.23+cpuavx2-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
-https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.23+cpuavx2-cp39-cp39-win_amd64.whl; platform_system == "Windows" and python_version == "3.9"
-https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.23+cpuavx2-cp38-cp38-win_amd64.whl; platform_system == "Windows" and python_version == "3.8"
+https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.23+cpuavx2-cp311-cp311-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
+https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.23+cpuavx2-cp310-cp310-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
+https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.23+cpuavx2-cp39-cp39-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.9"
+https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.23+cpuavx2-cp38-cp38-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.8"
+https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.23+cpuavx2-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
+https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.23+cpuavx2-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
+https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.23+cpuavx2-cp39-cp39-win_amd64.whl; platform_system == "Windows" and python_version == "3.9"
+https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.23+cpuavx2-cp38-cp38-win_amd64.whl; platform_system == "Windows" and python_version == "3.8"
# CUDA wheels
-https://github.com/jllllll/AutoGPTQ/releases/download/v0.5.1/auto_gptq-0.5.1+cu121-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
-https://github.com/jllllll/AutoGPTQ/releases/download/v0.5.1/auto_gptq-0.5.1+cu121-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
-https://github.com/jllllll/AutoGPTQ/releases/download/v0.5.1/auto_gptq-0.5.1+cu121-cp39-cp39-win_amd64.whl; platform_system == "Windows" and python_version == "3.9"
-https://github.com/jllllll/AutoGPTQ/releases/download/v0.5.1/auto_gptq-0.5.1+cu121-cp38-cp38-win_amd64.whl; platform_system == "Windows" and python_version == "3.8"
-https://github.com/jllllll/AutoGPTQ/releases/download/v0.5.1/auto_gptq-0.5.1+cu121-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
-https://github.com/jllllll/AutoGPTQ/releases/download/v0.5.1/auto_gptq-0.5.1+cu121-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
-https://github.com/jllllll/AutoGPTQ/releases/download/v0.5.1/auto_gptq-0.5.1+cu121-cp39-cp39-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.9"
-https://github.com/jllllll/AutoGPTQ/releases/download/v0.5.1/auto_gptq-0.5.1+cu121-cp38-cp38-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.8"
+https://github.com/jllllll/AutoGPTQ/releases/download/v0.6.0/auto_gptq-0.6.0+cu121-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
+https://github.com/jllllll/AutoGPTQ/releases/download/v0.6.0/auto_gptq-0.6.0+cu121-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
+https://github.com/jllllll/AutoGPTQ/releases/download/v0.6.0/auto_gptq-0.6.0+cu121-cp39-cp39-win_amd64.whl; platform_system == "Windows" and python_version == "3.9"
+https://github.com/jllllll/AutoGPTQ/releases/download/v0.6.0/auto_gptq-0.6.0+cu121-cp38-cp38-win_amd64.whl; platform_system == "Windows" and python_version == "3.8"
+https://github.com/jllllll/AutoGPTQ/releases/download/v0.6.0/auto_gptq-0.6.0+cu121-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
+https://github.com/jllllll/AutoGPTQ/releases/download/v0.6.0/auto_gptq-0.6.0+cu121-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
+https://github.com/jllllll/AutoGPTQ/releases/download/v0.6.0/auto_gptq-0.6.0+cu121-cp39-cp39-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.9"
+https://github.com/jllllll/AutoGPTQ/releases/download/v0.6.0/auto_gptq-0.6.0+cu121-cp38-cp38-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.8"
https://github.com/jllllll/exllama/releases/download/0.0.18/exllama-0.0.18+cu121-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
https://github.com/jllllll/exllama/releases/download/0.0.18/exllama-0.0.18+cu121-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
https://github.com/jllllll/exllama/releases/download/0.0.18/exllama-0.0.18+cu121-cp39-cp39-win_amd64.whl; platform_system == "Windows" and python_version == "3.9"
@@ -69,14 +69,14 @@ https://github.com/Dao-AILab/flash-attention/releases/download/v2.3.4/flash_attn
https://github.com/Dao-AILab/flash-attention/releases/download/v2.3.4/flash_attn-2.3.4+cu122torch2.1cxx11abiFALSE-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
https://github.com/Dao-AILab/flash-attention/releases/download/v2.3.4/flash_attn-2.3.4+cu122torch2.1cxx11abiFALSE-cp39-cp39-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.9"
https://github.com/Dao-AILab/flash-attention/releases/download/v2.3.4/flash_attn-2.3.4+cu122torch2.1cxx11abiFALSE-cp38-cp38-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.8"
-https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.23+cu121-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
-https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.23+cu121-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
-https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.23+cu121-cp39-cp39-win_amd64.whl; platform_system == "Windows" and python_version == "3.9"
-https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.23+cu121-cp38-cp38-win_amd64.whl; platform_system == "Windows" and python_version == "3.8"
-https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.23+cu121-cp311-cp311-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
-https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.23+cu121-cp310-cp310-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
-https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.23+cu121-cp39-cp39-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.9"
-https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.23+cu121-cp38-cp38-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.8"
+https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.23+cu121-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
+https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.23+cu121-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
+https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.23+cu121-cp39-cp39-win_amd64.whl; platform_system == "Windows" and python_version == "3.9"
+https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.23+cu121-cp38-cp38-win_amd64.whl; platform_system == "Windows" and python_version == "3.8"
+https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.23+cu121-cp311-cp311-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
+https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.23+cu121-cp310-cp310-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
+https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.23+cu121-cp39-cp39-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.9"
+https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.23+cu121-cp38-cp38-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.8"
https://github.com/jllllll/GPTQ-for-LLaMa-CUDA/releases/download/0.1.1/gptq_for_llama-0.1.1+cu121-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
https://github.com/jllllll/GPTQ-for-LLaMa-CUDA/releases/download/0.1.1/gptq_for_llama-0.1.1+cu121-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
https://github.com/jllllll/GPTQ-for-LLaMa-CUDA/releases/download/0.1.1/gptq_for_llama-0.1.1+cu121-cp39-cp39-win_amd64.whl; platform_system == "Windows" and python_version == "3.9"
diff --git a/requirements_amd.txt b/requirements_amd.txt
index 4fadcdf6..4f4c9369 100644
--- a/requirements_amd.txt
+++ b/requirements_amd.txt
@@ -27,28 +27,28 @@ bitsandbytes==0.38.1; platform_system != "Windows"
https://github.com/jllllll/bitsandbytes-windows-webui/releases/download/wheels/bitsandbytes-0.38.1-py3-none-win_amd64.whl; platform_system == "Windows"
# llama-cpp-python (CPU only, AVX2)
-https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.23+cpuavx2-cp311-cp311-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
-https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.23+cpuavx2-cp310-cp310-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
-https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.23+cpuavx2-cp39-cp39-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.9"
-https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.23+cpuavx2-cp38-cp38-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.8"
-https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.23+cpuavx2-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
-https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.23+cpuavx2-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
-https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.23+cpuavx2-cp39-cp39-win_amd64.whl; platform_system == "Windows" and python_version == "3.9"
-https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.23+cpuavx2-cp38-cp38-win_amd64.whl; platform_system == "Windows" and python_version == "3.8"
+https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.23+cpuavx2-cp311-cp311-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
+https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.23+cpuavx2-cp310-cp310-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
+https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.23+cpuavx2-cp39-cp39-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.9"
+https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.23+cpuavx2-cp38-cp38-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.8"
+https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.23+cpuavx2-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
+https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.23+cpuavx2-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
+https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.23+cpuavx2-cp39-cp39-win_amd64.whl; platform_system == "Windows" and python_version == "3.9"
+https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.23+cpuavx2-cp38-cp38-win_amd64.whl; platform_system == "Windows" and python_version == "3.8"
# AMD wheels
-https://github.com/jllllll/AutoGPTQ/releases/download/v0.5.1/auto_gptq-0.5.1+rocm5.6-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
-https://github.com/jllllll/AutoGPTQ/releases/download/v0.5.1/auto_gptq-0.5.1+rocm5.6-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
-https://github.com/jllllll/AutoGPTQ/releases/download/v0.5.1/auto_gptq-0.5.1+rocm5.6-cp39-cp39-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.9"
-https://github.com/jllllll/AutoGPTQ/releases/download/v0.5.1/auto_gptq-0.5.1+rocm5.6-cp38-cp38-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.8"
+https://github.com/jllllll/AutoGPTQ/releases/download/v0.6.0/auto_gptq-0.6.0+rocm5.6-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
+https://github.com/jllllll/AutoGPTQ/releases/download/v0.6.0/auto_gptq-0.6.0+rocm5.6-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
+https://github.com/jllllll/AutoGPTQ/releases/download/v0.6.0/auto_gptq-0.6.0+rocm5.6-cp39-cp39-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.9"
+https://github.com/jllllll/AutoGPTQ/releases/download/v0.6.0/auto_gptq-0.6.0+rocm5.6-cp38-cp38-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.8"
https://github.com/jllllll/exllama/releases/download/0.0.18/exllama-0.0.18+rocm5.6-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
https://github.com/jllllll/exllama/releases/download/0.0.18/exllama-0.0.18+rocm5.6-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
https://github.com/jllllll/exllama/releases/download/0.0.18/exllama-0.0.18+rocm5.6-cp39-cp39-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.9"
https://github.com/jllllll/exllama/releases/download/0.0.18/exllama-0.0.18+rocm5.6-cp38-cp38-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.8"
-https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/rocm/llama_cpp_python_cuda-0.2.19+rocm5.6.1-cp311-cp311-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
-https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/rocm/llama_cpp_python_cuda-0.2.19+rocm5.6.1-cp310-cp310-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
-https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/rocm/llama_cpp_python_cuda-0.2.19+rocm5.6.1-cp39-cp39-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.9"
-https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/rocm/llama_cpp_python_cuda-0.2.19+rocm5.6.1-cp38-cp38-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.8"
+https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/rocm/llama_cpp_python_cuda-0.2.23+rocm5.6.1-cp311-cp311-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
+https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/rocm/llama_cpp_python_cuda-0.2.23+rocm5.6.1-cp310-cp310-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
+https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/rocm/llama_cpp_python_cuda-0.2.23+rocm5.6.1-cp39-cp39-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.9"
+https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/rocm/llama_cpp_python_cuda-0.2.23+rocm5.6.1-cp38-cp38-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.8"
https://github.com/jllllll/GPTQ-for-LLaMa-CUDA/releases/download/0.1.1/gptq_for_llama-0.1.1+rocm5.6-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
https://github.com/jllllll/GPTQ-for-LLaMa-CUDA/releases/download/0.1.1/gptq_for_llama-0.1.1+rocm5.6-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
https://github.com/jllllll/GPTQ-for-LLaMa-CUDA/releases/download/0.1.1/gptq_for_llama-0.1.1+rocm5.6-cp39-cp39-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.9"
diff --git a/requirements_amd_noavx2.txt b/requirements_amd_noavx2.txt
index dec5561a..915444e1 100644
--- a/requirements_amd_noavx2.txt
+++ b/requirements_amd_noavx2.txt
@@ -27,20 +27,20 @@ bitsandbytes==0.38.1; platform_system != "Windows"
https://github.com/jllllll/bitsandbytes-windows-webui/releases/download/wheels/bitsandbytes-0.38.1-py3-none-win_amd64.whl; platform_system == "Windows"
# llama-cpp-python (CPU only, no AVX2)
-https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.23+cpuavx-cp311-cp311-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
-https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.23+cpuavx-cp310-cp310-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
-https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.23+cpuavx-cp39-cp39-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.9"
-https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.23+cpuavx-cp38-cp38-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.8"
-https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.23+cpuavx-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
-https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.23+cpuavx-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
-https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.23+cpuavx-cp39-cp39-win_amd64.whl; platform_system == "Windows" and python_version == "3.9"
-https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.23+cpuavx-cp38-cp38-win_amd64.whl; platform_system == "Windows" and python_version == "3.8"
+https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.23+cpuavx-cp311-cp311-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
+https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.23+cpuavx-cp310-cp310-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
+https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.23+cpuavx-cp39-cp39-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.9"
+https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.23+cpuavx-cp38-cp38-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.8"
+https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.23+cpuavx-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
+https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.23+cpuavx-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
+https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.23+cpuavx-cp39-cp39-win_amd64.whl; platform_system == "Windows" and python_version == "3.9"
+https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.23+cpuavx-cp38-cp38-win_amd64.whl; platform_system == "Windows" and python_version == "3.8"
# AMD wheels
-https://github.com/jllllll/AutoGPTQ/releases/download/v0.5.1/auto_gptq-0.5.1+rocm5.6-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
-https://github.com/jllllll/AutoGPTQ/releases/download/v0.5.1/auto_gptq-0.5.1+rocm5.6-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
-https://github.com/jllllll/AutoGPTQ/releases/download/v0.5.1/auto_gptq-0.5.1+rocm5.6-cp39-cp39-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.9"
-https://github.com/jllllll/AutoGPTQ/releases/download/v0.5.1/auto_gptq-0.5.1+rocm5.6-cp38-cp38-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.8"
+https://github.com/jllllll/AutoGPTQ/releases/download/v0.6.0/auto_gptq-0.6.0+rocm5.6-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
+https://github.com/jllllll/AutoGPTQ/releases/download/v0.6.0/auto_gptq-0.6.0+rocm5.6-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
+https://github.com/jllllll/AutoGPTQ/releases/download/v0.6.0/auto_gptq-0.6.0+rocm5.6-cp39-cp39-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.9"
+https://github.com/jllllll/AutoGPTQ/releases/download/v0.6.0/auto_gptq-0.6.0+rocm5.6-cp38-cp38-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.8"
https://github.com/jllllll/exllama/releases/download/0.0.18/exllama-0.0.18+rocm5.6-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
https://github.com/jllllll/exllama/releases/download/0.0.18/exllama-0.0.18+rocm5.6-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
https://github.com/jllllll/exllama/releases/download/0.0.18/exllama-0.0.18+rocm5.6-cp39-cp39-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.9"
diff --git a/requirements_apple_intel.txt b/requirements_apple_intel.txt
index 53d9e489..f57f054f 100644
--- a/requirements_apple_intel.txt
+++ b/requirements_apple_intel.txt
@@ -31,11 +31,11 @@ https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/meta
https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.19-cp310-cp310-macosx_11_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "20.0.0" and platform_release < "21.0.0" and python_version == "3.10"
https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.19-cp39-cp39-macosx_11_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "20.0.0" and platform_release < "21.0.0" and python_version == "3.9"
https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.19-cp38-cp38-macosx_11_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "20.0.0" and platform_release < "21.0.0" and python_version == "3.8"
-https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.19-cp311-cp311-macosx_12_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "21.0.0" and platform_release < "22.0.0" and python_version == "3.11"
-https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.19-cp310-cp310-macosx_12_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "21.0.0" and platform_release < "22.0.0" and python_version == "3.10"
-https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.19-cp39-cp39-macosx_12_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "21.0.0" and platform_release < "22.0.0" and python_version == "3.9"
-https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.19-cp38-cp38-macosx_12_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "21.0.0" and platform_release < "22.0.0" and python_version == "3.8"
-https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.19-cp311-cp311-macosx_14_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "23.0.0" and platform_release < "24.0.0" and python_version == "3.11"
-https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.19-cp310-cp310-macosx_14_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "23.0.0" and platform_release < "24.0.0" and python_version == "3.10"
-https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.19-cp39-cp39-macosx_14_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "23.0.0" and platform_release < "24.0.0" and python_version == "3.9"
-https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.19-cp38-cp38-macosx_14_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "23.0.0" and platform_release < "24.0.0" and python_version == "3.8"
+https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.23-cp311-cp311-macosx_12_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "21.0.0" and platform_release < "22.0.0" and python_version == "3.11"
+https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.23-cp310-cp310-macosx_12_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "21.0.0" and platform_release < "22.0.0" and python_version == "3.10"
+https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.23-cp39-cp39-macosx_12_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "21.0.0" and platform_release < "22.0.0" and python_version == "3.9"
+https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.23-cp38-cp38-macosx_12_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "21.0.0" and platform_release < "22.0.0" and python_version == "3.8"
+https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.23-cp311-cp311-macosx_14_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "23.0.0" and platform_release < "24.0.0" and python_version == "3.11"
+https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.23-cp310-cp310-macosx_14_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "23.0.0" and platform_release < "24.0.0" and python_version == "3.10"
+https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.23-cp39-cp39-macosx_14_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "23.0.0" and platform_release < "24.0.0" and python_version == "3.9"
+https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.23-cp38-cp38-macosx_14_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "23.0.0" and platform_release < "24.0.0" and python_version == "3.8"
diff --git a/requirements_apple_silicon.txt b/requirements_apple_silicon.txt
index 64427eb9..bb97db70 100644
--- a/requirements_apple_silicon.txt
+++ b/requirements_apple_silicon.txt
@@ -31,15 +31,15 @@ https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/meta
https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.19-cp310-cp310-macosx_11_0_arm64.whl; platform_system == "Darwin" and platform_release >= "20.0.0" and platform_release < "21.0.0" and python_version == "3.10"
https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.19-cp39-cp39-macosx_11_0_arm64.whl; platform_system == "Darwin" and platform_release >= "20.0.0" and platform_release < "21.0.0" and python_version == "3.9"
https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.19-cp38-cp38-macosx_11_0_arm64.whl; platform_system == "Darwin" and platform_release >= "20.0.0" and platform_release < "21.0.0" and python_version == "3.8"
-https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.19-cp311-cp311-macosx_12_0_arm64.whl; platform_system == "Darwin" and platform_release >= "21.0.0" and platform_release < "22.0.0" and python_version == "3.11"
-https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.19-cp310-cp310-macosx_12_0_arm64.whl; platform_system == "Darwin" and platform_release >= "21.0.0" and platform_release < "22.0.0" and python_version == "3.10"
-https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.19-cp39-cp39-macosx_12_0_arm64.whl; platform_system == "Darwin" and platform_release >= "21.0.0" and platform_release < "22.0.0" and python_version == "3.9"
-https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.19-cp38-cp38-macosx_12_0_arm64.whl; platform_system == "Darwin" and platform_release >= "21.0.0" and platform_release < "22.0.0" and python_version == "3.8"
-https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.19-cp311-cp311-macosx_13_0_arm64.whl; platform_system == "Darwin" and platform_release >= "22.0.0" and platform_release < "23.0.0" and python_version == "3.11"
-https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.19-cp310-cp310-macosx_13_0_arm64.whl; platform_system == "Darwin" and platform_release >= "22.0.0" and platform_release < "23.0.0" and python_version == "3.10"
-https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.19-cp39-cp39-macosx_13_0_arm64.whl; platform_system == "Darwin" and platform_release >= "22.0.0" and platform_release < "23.0.0" and python_version == "3.9"
-https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.19-cp38-cp38-macosx_13_0_arm64.whl; platform_system == "Darwin" and platform_release >= "22.0.0" and platform_release < "23.0.0" and python_version == "3.8"
-https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.19-cp311-cp311-macosx_14_0_arm64.whl; platform_system == "Darwin" and platform_release >= "23.0.0" and platform_release < "24.0.0" and python_version == "3.11"
-https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.19-cp310-cp310-macosx_14_0_arm64.whl; platform_system == "Darwin" and platform_release >= "23.0.0" and platform_release < "24.0.0" and python_version == "3.10"
-https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.19-cp39-cp39-macosx_14_0_arm64.whl; platform_system == "Darwin" and platform_release >= "23.0.0" and platform_release < "24.0.0" and python_version == "3.9"
-https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.19-cp38-cp38-macosx_14_0_arm64.whl; platform_system == "Darwin" and platform_release >= "23.0.0" and platform_release < "24.0.0" and python_version == "3.8"
+https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.23-cp311-cp311-macosx_12_0_arm64.whl; platform_system == "Darwin" and platform_release >= "21.0.0" and platform_release < "22.0.0" and python_version == "3.11"
+https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.23-cp310-cp310-macosx_12_0_arm64.whl; platform_system == "Darwin" and platform_release >= "21.0.0" and platform_release < "22.0.0" and python_version == "3.10"
+https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.23-cp39-cp39-macosx_12_0_arm64.whl; platform_system == "Darwin" and platform_release >= "21.0.0" and platform_release < "22.0.0" and python_version == "3.9"
+https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.23-cp38-cp38-macosx_12_0_arm64.whl; platform_system == "Darwin" and platform_release >= "21.0.0" and platform_release < "22.0.0" and python_version == "3.8"
+https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.23-cp311-cp311-macosx_13_0_arm64.whl; platform_system == "Darwin" and platform_release >= "22.0.0" and platform_release < "23.0.0" and python_version == "3.11"
+https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.23-cp310-cp310-macosx_13_0_arm64.whl; platform_system == "Darwin" and platform_release >= "22.0.0" and platform_release < "23.0.0" and python_version == "3.10"
+https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.23-cp39-cp39-macosx_13_0_arm64.whl; platform_system == "Darwin" and platform_release >= "22.0.0" and platform_release < "23.0.0" and python_version == "3.9"
+https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.23-cp38-cp38-macosx_13_0_arm64.whl; platform_system == "Darwin" and platform_release >= "22.0.0" and platform_release < "23.0.0" and python_version == "3.8"
+https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.23-cp311-cp311-macosx_14_0_arm64.whl; platform_system == "Darwin" and platform_release >= "23.0.0" and platform_release < "24.0.0" and python_version == "3.11"
+https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.23-cp310-cp310-macosx_14_0_arm64.whl; platform_system == "Darwin" and platform_release >= "23.0.0" and platform_release < "24.0.0" and python_version == "3.10"
+https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.23-cp39-cp39-macosx_14_0_arm64.whl; platform_system == "Darwin" and platform_release >= "23.0.0" and platform_release < "24.0.0" and python_version == "3.9"
+https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.23-cp38-cp38-macosx_14_0_arm64.whl; platform_system == "Darwin" and platform_release >= "23.0.0" and platform_release < "24.0.0" and python_version == "3.8"
diff --git a/requirements_cpu_only.txt b/requirements_cpu_only.txt
index 3f1bb5e6..2925ba77 100644
--- a/requirements_cpu_only.txt
+++ b/requirements_cpu_only.txt
@@ -27,11 +27,11 @@ bitsandbytes==0.41.1; platform_system != "Windows"
https://github.com/jllllll/bitsandbytes-windows-webui/releases/download/wheels/bitsandbytes-0.41.1-py3-none-win_amd64.whl; platform_system == "Windows"
# llama-cpp-python (CPU only, AVX2)
-https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.23+cpuavx2-cp311-cp311-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
-https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.23+cpuavx2-cp310-cp310-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
-https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.23+cpuavx2-cp39-cp39-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.9"
-https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.23+cpuavx2-cp38-cp38-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.8"
-https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.23+cpuavx2-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
-https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.23+cpuavx2-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
-https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.23+cpuavx2-cp39-cp39-win_amd64.whl; platform_system == "Windows" and python_version == "3.9"
-https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.23+cpuavx2-cp38-cp38-win_amd64.whl; platform_system == "Windows" and python_version == "3.8"
+https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.23+cpuavx2-cp311-cp311-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
+https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.23+cpuavx2-cp310-cp310-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
+https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.23+cpuavx2-cp39-cp39-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.9"
+https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.23+cpuavx2-cp38-cp38-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.8"
+https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.23+cpuavx2-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
+https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.23+cpuavx2-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
+https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.23+cpuavx2-cp39-cp39-win_amd64.whl; platform_system == "Windows" and python_version == "3.9"
+https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.23+cpuavx2-cp38-cp38-win_amd64.whl; platform_system == "Windows" and python_version == "3.8"
diff --git a/requirements_cpu_only_noavx2.txt b/requirements_cpu_only_noavx2.txt
index fe1a5139..cc6fe912 100644
--- a/requirements_cpu_only_noavx2.txt
+++ b/requirements_cpu_only_noavx2.txt
@@ -27,11 +27,11 @@ bitsandbytes==0.41.1; platform_system != "Windows"
https://github.com/jllllll/bitsandbytes-windows-webui/releases/download/wheels/bitsandbytes-0.41.1-py3-none-win_amd64.whl; platform_system == "Windows"
# llama-cpp-python (CPU only, no AVX2)
-https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.23+cpuavx-cp311-cp311-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
-https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.23+cpuavx-cp310-cp310-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
-https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.23+cpuavx-cp39-cp39-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.9"
-https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.23+cpuavx-cp38-cp38-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.8"
-https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.23+cpuavx-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
-https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.23+cpuavx-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
-https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.23+cpuavx-cp39-cp39-win_amd64.whl; platform_system == "Windows" and python_version == "3.9"
-https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.23+cpuavx-cp38-cp38-win_amd64.whl; platform_system == "Windows" and python_version == "3.8"
+https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.23+cpuavx-cp311-cp311-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
+https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.23+cpuavx-cp310-cp310-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
+https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.23+cpuavx-cp39-cp39-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.9"
+https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.23+cpuavx-cp38-cp38-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.8"
+https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.23+cpuavx-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
+https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.23+cpuavx-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
+https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.23+cpuavx-cp39-cp39-win_amd64.whl; platform_system == "Windows" and python_version == "3.9"
+https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.23+cpuavx-cp38-cp38-win_amd64.whl; platform_system == "Windows" and python_version == "3.8"
diff --git a/requirements_noavx2.txt b/requirements_noavx2.txt
index 3c5f83dd..33a14d2a 100644
--- a/requirements_noavx2.txt
+++ b/requirements_noavx2.txt
@@ -27,24 +27,24 @@ bitsandbytes==0.41.1; platform_system != "Windows"
https://github.com/jllllll/bitsandbytes-windows-webui/releases/download/wheels/bitsandbytes-0.41.1-py3-none-win_amd64.whl; platform_system == "Windows"
# llama-cpp-python (CPU only, no AVX2)
-https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.23+cpuavx-cp311-cp311-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
-https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.23+cpuavx-cp310-cp310-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
-https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.23+cpuavx-cp39-cp39-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.9"
-https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.23+cpuavx-cp38-cp38-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.8"
-https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.23+cpuavx-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
-https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.23+cpuavx-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
-https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.23+cpuavx-cp39-cp39-win_amd64.whl; platform_system == "Windows" and python_version == "3.9"
-https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.23+cpuavx-cp38-cp38-win_amd64.whl; platform_system == "Windows" and python_version == "3.8"
+https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.23+cpuavx-cp311-cp311-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
+https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.23+cpuavx-cp310-cp310-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
+https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.23+cpuavx-cp39-cp39-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.9"
+https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.23+cpuavx-cp38-cp38-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.8"
+https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.23+cpuavx-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
+https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.23+cpuavx-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
+https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.23+cpuavx-cp39-cp39-win_amd64.whl; platform_system == "Windows" and python_version == "3.9"
+https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.23+cpuavx-cp38-cp38-win_amd64.whl; platform_system == "Windows" and python_version == "3.8"
# CUDA wheels
-https://github.com/jllllll/AutoGPTQ/releases/download/v0.5.1/auto_gptq-0.5.1+cu121-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
-https://github.com/jllllll/AutoGPTQ/releases/download/v0.5.1/auto_gptq-0.5.1+cu121-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
-https://github.com/jllllll/AutoGPTQ/releases/download/v0.5.1/auto_gptq-0.5.1+cu121-cp39-cp39-win_amd64.whl; platform_system == "Windows" and python_version == "3.9"
-https://github.com/jllllll/AutoGPTQ/releases/download/v0.5.1/auto_gptq-0.5.1+cu121-cp38-cp38-win_amd64.whl; platform_system == "Windows" and python_version == "3.8"
-https://github.com/jllllll/AutoGPTQ/releases/download/v0.5.1/auto_gptq-0.5.1+cu121-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
-https://github.com/jllllll/AutoGPTQ/releases/download/v0.5.1/auto_gptq-0.5.1+cu121-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
-https://github.com/jllllll/AutoGPTQ/releases/download/v0.5.1/auto_gptq-0.5.1+cu121-cp39-cp39-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.9"
-https://github.com/jllllll/AutoGPTQ/releases/download/v0.5.1/auto_gptq-0.5.1+cu121-cp38-cp38-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.8"
+https://github.com/jllllll/AutoGPTQ/releases/download/v0.6.0/auto_gptq-0.6.0+cu121-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
+https://github.com/jllllll/AutoGPTQ/releases/download/v0.6.0/auto_gptq-0.6.0+cu121-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
+https://github.com/jllllll/AutoGPTQ/releases/download/v0.6.0/auto_gptq-0.6.0+cu121-cp39-cp39-win_amd64.whl; platform_system == "Windows" and python_version == "3.9"
+https://github.com/jllllll/AutoGPTQ/releases/download/v0.6.0/auto_gptq-0.6.0+cu121-cp38-cp38-win_amd64.whl; platform_system == "Windows" and python_version == "3.8"
+https://github.com/jllllll/AutoGPTQ/releases/download/v0.6.0/auto_gptq-0.6.0+cu121-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
+https://github.com/jllllll/AutoGPTQ/releases/download/v0.6.0/auto_gptq-0.6.0+cu121-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
+https://github.com/jllllll/AutoGPTQ/releases/download/v0.6.0/auto_gptq-0.6.0+cu121-cp39-cp39-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.9"
+https://github.com/jllllll/AutoGPTQ/releases/download/v0.6.0/auto_gptq-0.6.0+cu121-cp38-cp38-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.8"
https://github.com/jllllll/exllama/releases/download/0.0.18/exllama-0.0.18+cu121-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
https://github.com/jllllll/exllama/releases/download/0.0.18/exllama-0.0.18+cu121-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
https://github.com/jllllll/exllama/releases/download/0.0.18/exllama-0.0.18+cu121-cp39-cp39-win_amd64.whl; platform_system == "Windows" and python_version == "3.9"
@@ -69,14 +69,14 @@ https://github.com/Dao-AILab/flash-attention/releases/download/v2.3.4/flash_attn
https://github.com/Dao-AILab/flash-attention/releases/download/v2.3.4/flash_attn-2.3.4+cu122torch2.1cxx11abiFALSE-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
https://github.com/Dao-AILab/flash-attention/releases/download/v2.3.4/flash_attn-2.3.4+cu122torch2.1cxx11abiFALSE-cp39-cp39-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.9"
https://github.com/Dao-AILab/flash-attention/releases/download/v2.3.4/flash_attn-2.3.4+cu122torch2.1cxx11abiFALSE-cp38-cp38-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.8"
-https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.23+cu121avx-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
-https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.23+cu121avx-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
-https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.23+cu121avx-cp39-cp39-win_amd64.whl; platform_system == "Windows" and python_version == "3.9"
-https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.23+cu121avx-cp38-cp38-win_amd64.whl; platform_system == "Windows" and python_version == "3.8"
-https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.23+cu121avx-cp311-cp311-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
-https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.23+cu121avx-cp310-cp310-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
-https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.23+cu121avx-cp39-cp39-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.9"
-https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.23+cu121avx-cp38-cp38-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.8"
+https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.23+cu121avx-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
+https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.23+cu121avx-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
+https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.23+cu121avx-cp39-cp39-win_amd64.whl; platform_system == "Windows" and python_version == "3.9"
+https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.23+cu121avx-cp38-cp38-win_amd64.whl; platform_system == "Windows" and python_version == "3.8"
+https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.23+cu121avx-cp311-cp311-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
+https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.23+cu121avx-cp310-cp310-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
+https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.23+cu121avx-cp39-cp39-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.9"
+https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.23+cu121avx-cp38-cp38-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.8"
https://github.com/jllllll/GPTQ-for-LLaMa-CUDA/releases/download/0.1.1/gptq_for_llama-0.1.1+cu121-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
https://github.com/jllllll/GPTQ-for-LLaMa-CUDA/releases/download/0.1.1/gptq_for_llama-0.1.1+cu121-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
https://github.com/jllllll/GPTQ-for-LLaMa-CUDA/releases/download/0.1.1/gptq_for_llama-0.1.1+cu121-cp39-cp39-win_amd64.whl; platform_system == "Windows" and python_version == "3.9"