Mirrors/text-generation-webui
1
0
Fork 0
mirror of https://github.com/oobabooga/text-generation-webui.git synced 2024-11-22 08:07:56 +01:00
Code Issues Packages Projects Releases Wiki Activity

Bump llama-cpp-python to 0.2.64, use official wheels (#5921)

Browse Source
This commit is contained in:
oobabooga 2024-04-23 23:17:05 -03:00 committed by GitHub
parent 0877741b03
commit 9b623b8a78
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
16 changed files with 53 additions and 325 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

14
README.md
View File

@ -107,14 +107,11 @@ pip install -r <requirements file according to table below>
Requirements file to use: Requirements file to use:
| GPU | CPU | requirements file to use | | GPU | requirements file to use |
|--------|---------|---------| |--------|---------|---------|
| NVIDIA | has AVX2 | `requirements.txt` | | NVIDIA | `requirements.txt` |
| NVIDIA | no AVX2 | `requirements_noavx2.txt` | | AMD | `requirements_amd.txt` |
| AMD | has AVX2 | `requirements_amd.txt` | | CPU only | `requirements_cpu_only.txt` |
| AMD | no AVX2 | `requirements_amd_noavx2.txt` |
| CPU only | has AVX2 | `requirements_cpu_only.txt` |
| CPU only | no AVX2 | `requirements_cpu_only_noavx2.txt` |
| Apple | Intel | `requirements_apple_intel.txt` | | Apple | Intel | `requirements_apple_intel.txt` |
| Apple | Apple Silicon | `requirements_apple_silicon.txt` | | Apple | Apple Silicon | `requirements_apple_silicon.txt` |
@ -132,7 +129,7 @@ Then browse to
##### AMD GPU on Windows ##### AMD GPU on Windows
1) Use `requirements_cpu_only.txt` or `requirements_cpu_only_noavx2.txt` in the command above. 1) Use `requirements_cpu_only.txt` in the command above.
2) Manually install llama-cpp-python using the appropriate command for your hardware: [Installation from PyPI](https://github.com/abetlen/llama-cpp-python#installation-with-hardware-acceleration). 2) Manually install llama-cpp-python using the appropriate command for your hardware: [Installation from PyPI](https://github.com/abetlen/llama-cpp-python#installation-with-hardware-acceleration).
* Use the `LLAMA_HIPBLAS=on` toggle. * Use the `LLAMA_HIPBLAS=on` toggle.
@ -255,7 +252,6 @@ List of command-line flags
| Flag | Description | | Flag | Description |
|-------------|-------------| |-------------|-------------|
| `--tensorcores` | Use llama-cpp-python compiled with tensor cores support. This increases performance on RTX cards. NVIDIA only. |
| `--n_ctx N_CTX` | Size of the prompt context. | | `--n_ctx N_CTX` | Size of the prompt context. |
| `--threads` | Number of threads to use. | | `--threads` | Number of threads to use. |
| `--threads-batch THREADS_BATCH` | Number of threads to use for batches/prompt processing. | | `--threads-batch THREADS_BATCH` | Number of threads to use for batches/prompt processing. |

4
docs/04 - Model Tab.md
View File

@ -21,7 +21,7 @@ Options:
* **alpha_value**: Used to extend the context length of a model with a minor loss in quality. I have measured 1.75 to be optimal for 1.5x context, and 2.5 for 2x context. That is, with alpha = 2.5 you can make a model with 4096 context length go to 8192 context length. * **alpha_value**: Used to extend the context length of a model with a minor loss in quality. I have measured 1.75 to be optimal for 1.5x context, and 2.5 for 2x context. That is, with alpha = 2.5 you can make a model with 4096 context length go to 8192 context length.
* **rope_freq_base**: Originally another way to write "alpha_value", it ended up becoming a necessary parameter for some models like CodeLlama, which was fine-tuned with this set to 1000000 and hence needs to be loaded with it set to 1000000 as well. * **rope_freq_base**: Originally another way to write "alpha_value", it ended up becoming a necessary parameter for some models like CodeLlama, which was fine-tuned with this set to 1000000 and hence needs to be loaded with it set to 1000000 as well.
* **compress_pos_emb**: The first and original context-length extension method, discovered by [kaiokendev](https://kaiokendev.github.io/til). When set to 2, the context length is doubled, 3 and it's tripled, etc. It should only be used for models that have been fine-tuned with this parameter set to different than 1. For models that have not been tuned to have greater context length, alpha_value will lead to a smaller accuracy loss. * **compress_pos_emb**: The first and original context-length extension method, discovered by [kaiokendev](https://kaiokendev.github.io/til). When set to 2, the context length is doubled, 3 and it's tripled, etc. It should only be used for models that have been fine-tuned with this parameter set to different than 1. For models that have not been tuned to have greater context length, alpha_value will lead to a smaller accuracy loss.
* **cpu**: Loads the model in CPU mode using Pytorch. The model will be loaded in 32-bit precision, so a lot of RAM will be used. CPU inference with transformers is older than llama.cpp and it works, but it's a lot slower. Note: this parameter has a different interpretation in the llama.cpp loader (see below). * **cpu**: Loads the model in CPU mode using Pytorch. The model will be loaded in 32-bit precision, so a lot of RAM will be used. CPU inference with transformers is older than llama.cpp and it works, but it's a lot slower.
* **load-in-8bit**: Load the model in 8-bit precision using bitsandbytes. The 8-bit kernel in that library has been optimized for training and not inference, so load-in-8bit is slower than load-in-4bit (but more accurate). * **load-in-8bit**: Load the model in 8-bit precision using bitsandbytes. The 8-bit kernel in that library has been optimized for training and not inference, so load-in-8bit is slower than load-in-4bit (but more accurate).
* **bf16**: Use bfloat16 precision instead of float16 (the default). Only applies when quantization is not used. * **bf16**: Use bfloat16 precision instead of float16 (the default). Only applies when quantization is not used.
* **auto-devices**: When checked, the backend will try to guess a reasonable value for "gpu-memory" to allow you to load a model with CPU offloading. I recommend just setting "gpu-memory" manually instead. This parameter is also needed for loading GPTQ models, in which case it needs to be checked before loading the model. * **auto-devices**: When checked, the backend will try to guess a reasonable value for "gpu-memory" to allow you to load a model with CPU offloading. I recommend just setting "gpu-memory" manually instead. This parameter is also needed for loading GPTQ models, in which case it needs to be checked before loading the model.
@ -84,9 +84,7 @@ Example: https://huggingface.co/TheBloke/Llama-2-7b-Chat-GGUF
* **n_batch**: Batch size for prompt processing. Higher values are supposed to make generation faster, but I have never obtained any benefit from changing this value. * **n_batch**: Batch size for prompt processing. Higher values are supposed to make generation faster, but I have never obtained any benefit from changing this value.
* **threads**: Number of threads. Recommended value: your number of physical cores. * **threads**: Number of threads. Recommended value: your number of physical cores.
* **threads_batch**: Number of threads for batch processing. Recommended value: your total number of cores (physical + virtual). * **threads_batch**: Number of threads for batch processing. Recommended value: your total number of cores (physical + virtual).
* **tensorcores**: Use llama.cpp compiled with "tensor cores" support, which improves performance on NVIDIA RTX cards in most cases.
* **streamingllm**: Experimental feature to avoid re-evaluating the entire prompt when part of it is removed, for instance, when you hit the context length for the model in chat mode and an old message is removed. * **streamingllm**: Experimental feature to avoid re-evaluating the entire prompt when part of it is removed, for instance, when you hit the context length for the model in chat mode and an old message is removed.
* **cpu**: Force a version of llama.cpp compiled without GPU acceleration to be used. Can usually be ignored. Only set this if you want to use CPU only and llama.cpp doesn't work otherwise.
* **no_mul_mat_q**: Disable the mul_mat_q kernel. This kernel usually improves generation speed significantly. This option to disable it is included in case it doesn't work on some system. * **no_mul_mat_q**: Disable the mul_mat_q kernel. This kernel usually improves generation speed significantly. This option to disable it is included in case it doesn't work on some system.
* **no-mmap**: Loads the model into memory at once, possibly preventing I/O operations later on at the cost of a longer load time. * **no-mmap**: Loads the model into memory at once, possibly preventing I/O operations later on at the cost of a longer load time.
* **mlock**: Force the system to keep the model in RAM rather than swapping or compressing (no idea what this means, never used it). * **mlock**: Force the system to keep the model in RAM rather than swapping or compressing (no idea what this means, never used it).

18
modules/llama_cpp_python_hijack.py
View File

@ -1,25 +1,11 @@
from typing import Sequence from typing import Sequence
import llama_cpp
from tqdm import tqdm from tqdm import tqdm
from modules import shared from modules import shared
from modules.cache_utils import process_llamacpp_cache from modules.cache_utils import process_llamacpp_cache
try:
import llama_cpp
except:
llama_cpp = None
try:
import llama_cpp_cuda
except:
llama_cpp_cuda = None
try:
import llama_cpp_cuda_tensorcores
except:
llama_cpp_cuda_tensorcores = None
def eval_with_progress(self, tokens: Sequence[int]): def eval_with_progress(self, tokens: Sequence[int]):
""" """
@ -81,7 +67,7 @@ def monkey_patch_generate(lib):
lib.Llama.generate = my_generate lib.Llama.generate = my_generate
for lib in [llama_cpp, llama_cpp_cuda, llama_cpp_cuda_tensorcores]: for lib in [llama_cpp]:
if lib is not None: if lib is not None:
lib.Llama.eval = eval_with_progress lib.Llama.eval = eval_with_progress
monkey_patch_generate(lib) monkey_patch_generate(lib)

31
modules/llamacpp_hf.py
View File

@ -2,6 +2,7 @@ import os
from pathlib import Path from pathlib import Path
from typing import Any, Dict, Optional, Union from typing import Any, Dict, Optional, Union
import llama_cpp
import torch import torch
from torch.nn import CrossEntropyLoss from torch.nn import CrossEntropyLoss
from transformers import GenerationConfig, PretrainedConfig, PreTrainedModel from transformers import GenerationConfig, PretrainedConfig, PreTrainedModel
@ -10,32 +11,6 @@ from transformers.modeling_outputs import CausalLMOutputWithPast
from modules import RoPE, llama_cpp_python_hijack, shared from modules import RoPE, llama_cpp_python_hijack, shared
from modules.logging_colors import logger from modules.logging_colors import logger
try:
import llama_cpp
except:
llama_cpp = None
try:
import llama_cpp_cuda
except:
llama_cpp_cuda = None
try:
import llama_cpp_cuda_tensorcores
except:
llama_cpp_cuda_tensorcores = None
def llama_cpp_lib():
if shared.args.cpu and llama_cpp is not None:
return llama_cpp
elif shared.args.tensorcores and llama_cpp_cuda_tensorcores is not None:
return llama_cpp_cuda_tensorcores
elif llama_cpp_cuda is not None:
return llama_cpp_cuda
else:
return llama_cpp
class LlamacppHF(PreTrainedModel): class LlamacppHF(PreTrainedModel):
def __init__(self, model, path): def __init__(self, model, path):
@ -57,7 +32,7 @@ class LlamacppHF(PreTrainedModel):
'n_tokens': self.model.n_tokens, 'n_tokens': self.model.n_tokens,
'input_ids': self.model.input_ids.copy(), 'input_ids': self.model.input_ids.copy(),
'scores': self.model.scores.copy(), 'scores': self.model.scores.copy(),
'ctx': llama_cpp_lib().llama_new_context_with_model(model.model, model.context_params) 'ctx': llama_cpp.llama_new_context_with_model(model.model, model.context_params)
} }
def _validate_model_class(self): def _validate_model_class(self):
@ -220,7 +195,7 @@ class LlamacppHF(PreTrainedModel):
'split_mode': 1 if not shared.args.row_split else 2 'split_mode': 1 if not shared.args.row_split else 2
} }
Llama = llama_cpp_lib().Llama Llama = llama_cpp.Llama
model = Llama(**params) model = Llama(**params)
return LlamacppHF(model, model_file) return LlamacppHF(model, model_file)

35
modules/llamacpp_model.py
View File

@ -1,6 +1,7 @@
import re import re
from functools import partial from functools import partial
import llama_cpp
import numpy as np import numpy as np
import torch import torch
@ -9,32 +10,6 @@ from modules.callbacks import Iteratorize
from modules.logging_colors import logger from modules.logging_colors import logger
from modules.text_generation import get_max_prompt_length from modules.text_generation import get_max_prompt_length
try:
import llama_cpp
except:
llama_cpp = None
try:
import llama_cpp_cuda
except:
llama_cpp_cuda = None
try:
import llama_cpp_cuda_tensorcores
except:
llama_cpp_cuda_tensorcores = None
def llama_cpp_lib():
if shared.args.cpu and llama_cpp is not None:
return llama_cpp
elif shared.args.tensorcores and llama_cpp_cuda_tensorcores is not None:
return llama_cpp_cuda_tensorcores
elif llama_cpp_cuda is not None:
return llama_cpp_cuda
else:
return llama_cpp
def ban_eos_logits_processor(eos_token, input_ids, logits): def ban_eos_logits_processor(eos_token, input_ids, logits):
logits[eos_token] = -float('inf') logits[eos_token] = -float('inf')
@ -60,8 +35,8 @@ class LlamaCppModel:
@classmethod @classmethod
def from_pretrained(self, path): def from_pretrained(self, path):
Llama = llama_cpp_lib().Llama Llama = llama_cpp.Llama
LlamaCache = llama_cpp_lib().LlamaCache LlamaCache = llama_cpp.LlamaCache
result = self() result = self()
cache_capacity = 0 cache_capacity = 0
@ -126,12 +101,12 @@ class LlamaCppModel:
if string != self.grammar_string: if string != self.grammar_string:
self.grammar_string = string self.grammar_string = string
if string.strip() != '': if string.strip() != '':
self.grammar = llama_cpp_lib().LlamaGrammar.from_string(string) self.grammar = llama_cpp.LlamaGrammar.from_string(string)
else: else:
self.grammar = None self.grammar = None
def generate(self, prompt, state, callback=None): def generate(self, prompt, state, callback=None):
LogitsProcessorList = llama_cpp_lib().LogitsProcessorList LogitsProcessorList = llama_cpp.LogitsProcessorList
prompt = prompt if type(prompt) is str else prompt.decode() prompt = prompt if type(prompt) is str else prompt.decode()
# Handle truncation # Handle truncation

4
modules/loaders.py
View File

@ -41,11 +41,9 @@ loaders_and_params = OrderedDict({
'alpha_value', 'alpha_value',
'rope_freq_base', 'rope_freq_base',
'compress_pos_emb', 'compress_pos_emb',
'cpu',
'numa', 'numa',
'no_offload_kqv', 'no_offload_kqv',
'row_split', 'row_split',
'tensorcores',
'streaming_llm', 'streaming_llm',
'attention_sink_size', 'attention_sink_size',
], ],
@ -62,7 +60,6 @@ loaders_and_params = OrderedDict({
'alpha_value', 'alpha_value',
'rope_freq_base', 'rope_freq_base',
'compress_pos_emb', 'compress_pos_emb',
'cpu',
'numa', 'numa',
'cfg_cache', 'cfg_cache',
'trust_remote_code', 'trust_remote_code',
@ -70,7 +67,6 @@ loaders_and_params = OrderedDict({
'logits_all', 'logits_all',
'no_offload_kqv', 'no_offload_kqv',
'row_split', 'row_split',
'tensorcores',
'streaming_llm', 'streaming_llm',
'attention_sink_size', 'attention_sink_size',
'llamacpp_HF_info', 'llamacpp_HF_info',

6
modules/shared.py
View File

@ -113,7 +113,6 @@ group.add_argument('--quant_type', type=str, default='nf4', help='quant_type for
# llama.cpp # llama.cpp
group = parser.add_argument_group('llama.cpp') group = parser.add_argument_group('llama.cpp')
group.add_argument('--tensorcores', action='store_true', help='Use llama-cpp-python compiled with tensor cores support. This increases performance on RTX cards. NVIDIA only.')
group.add_argument('--n_ctx', type=int, default=2048, help='Size of the prompt context.') group.add_argument('--n_ctx', type=int, default=2048, help='Size of the prompt context.')
group.add_argument('--threads', type=int, default=0, help='Number of threads to use.') group.add_argument('--threads', type=int, default=0, help='Number of threads to use.')
group.add_argument('--threads-batch', type=int, default=0, help='Number of threads to use for batches/prompt processing.') group.add_argument('--threads-batch', type=int, default=0, help='Number of threads to use for batches/prompt processing.')
@ -204,7 +203,8 @@ group = parser.add_argument_group('Multimodal')
group.add_argument('--multimodal-pipeline', type=str, default=None, help='The multimodal pipeline to use. Examples: llava-7b, llava-13b.') group.add_argument('--multimodal-pipeline', type=str, default=None, help='The multimodal pipeline to use. Examples: llava-7b, llava-13b.')
# Deprecated parameters # Deprecated parameters
# group = parser.add_argument_group('Deprecated') group = parser.add_argument_group('Deprecated')
group.add_argument('--tensorcores', action='store_true', help='DEPRECATED')
args = parser.parse_args() args = parser.parse_args()
args_defaults = parser.parse_args([]) args_defaults = parser.parse_args([])
@ -214,7 +214,7 @@ for arg in sys.argv[1:]:
if hasattr(args, arg): if hasattr(args, arg):
provided_arguments.append(arg) provided_arguments.append(arg)
deprecated_args = [] deprecated_args = ['tensorcores']
def do_cmd_flags_warnings(): def do_cmd_flags_warnings():

35
one_click.py
View File

@ -58,32 +58,6 @@ def is_x86_64():
return platform.machine() == "x86_64" return platform.machine() == "x86_64"
def cpu_has_avx2():
try:
import cpuinfo
info = cpuinfo.get_cpu_info()
if 'avx2' in info['flags']:
return True
else:
return False
except:
return True
def cpu_has_amx():
try:
import cpuinfo
info = cpuinfo.get_cpu_info()
if 'amx' in info['flags']:
return True
else:
return False
except:
return True
def torch_version(): def torch_version():
site_packages_path = None site_packages_path = None
for sitedir in site.getsitepackages(): for sitedir in site.getsitepackages():
@ -305,7 +279,7 @@ def install_webui():
# Install Git and then Pytorch # Install Git and then Pytorch
print_big_message("Installing PyTorch.") print_big_message("Installing PyTorch.")
run_cmd(f"conda install -y -k ninja git && {install_pytorch} && python -m pip install py-cpuinfo==9.0.0", assert_success=True, environment=True) run_cmd(f"conda install -y -k ninja git && {install_pytorch}", assert_success=True, environment=True)
if selected_gpu == "INTEL": if selected_gpu == "INTEL":
# Install oneAPI dependencies via conda # Install oneAPI dependencies via conda
@ -372,13 +346,13 @@ def update_requirements(initial_installation=False, pull=True):
is_cpu = '+cpu' in torver # 2.0.1+cpu is_cpu = '+cpu' in torver # 2.0.1+cpu
if is_rocm: if is_rocm:
base_requirements = "requirements_amd" + ("_noavx2" if not cpu_has_avx2() else "") + ".txt" base_requirements = "requirements_amd.txt"
elif is_cpu or is_intel: elif is_cpu or is_intel:
base_requirements = "requirements_cpu_only" + ("_noavx2" if not cpu_has_avx2() else "") + ".txt" base_requirements = "requirements_cpu_only.txt"
elif is_macos(): elif is_macos():
base_requirements = "requirements_apple_" + ("intel" if is_x86_64() else "silicon") + ".txt" base_requirements = "requirements_apple_" + ("intel" if is_x86_64() else "silicon") + ".txt"
else: else:
base_requirements = "requirements" + ("_noavx2" if not cpu_has_avx2() else "") + ".txt" base_requirements = "requirements.txt"
requirements_file = base_requirements requirements_file = base_requirements
@ -389,6 +363,7 @@ def update_requirements(initial_installation=False, pull=True):
textgen_requirements = open(requirements_file).read().splitlines() textgen_requirements = open(requirements_file).read().splitlines()
if is_cuda118: if is_cuda118:
textgen_requirements = [req.replace('+cu121', '+cu118').replace('+cu122', '+cu118') for req in textgen_requirements] textgen_requirements = [req.replace('+cu121', '+cu118').replace('+cu122', '+cu118') for req in textgen_requirements]
textgen_requirements = [req for req in textgen_requirements if '-cu121' not in req]
if is_windows() and is_cuda118: # No flash-attention on Windows for CUDA 11 if is_windows() and is_cuda118: # No flash-attention on Windows for CUDA 11
textgen_requirements = [req for req in textgen_requirements if 'oobabooga/flash-attention' not in req] textgen_requirements = [req for req in textgen_requirements if 'oobabooga/flash-attention' not in req]

22
requirements.txt
View File

@ -33,23 +33,11 @@ flask_cloudflared==0.0.14
sse-starlette==1.6.5 sse-starlette==1.6.5
tiktoken tiktoken
# llama-cpp-python (CPU only, AVX2) # llama-cpp-python (CUDA)
https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.61+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/abetlen/llama-cpp-python/releases/download/v0.2.64-cu121/llama_cpp_python-0.2.64-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-0.2.61+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/abetlen/llama-cpp-python/releases/download/v0.2.64-cu121/llama_cpp_python-0.2.64-cp311-cp311-linux_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-0.2.61+cpuavx2-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11" https://github.com/abetlen/llama-cpp-python/releases/download/v0.2.64-cu121/llama_cpp_python-0.2.64-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-0.2.61+cpuavx2-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10" https://github.com/abetlen/llama-cpp-python/releases/download/v0.2.64-cu121/llama_cpp_python-0.2.64-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
# llama-cpp-python (CUDA, no tensor cores)
https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.61+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-0.2.61+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-0.2.61+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-0.2.61+cu121-cp310-cp310-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
# llama-cpp-python (CUDA, tensor cores)
https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda_tensorcores-0.2.61+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_tensorcores-0.2.61+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_tensorcores-0.2.61+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_tensorcores-0.2.61+cu121-cp310-cp310-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
# CUDA wheels # CUDA wheels
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-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"

12
requirements_amd.txt
View File

@ -31,15 +31,13 @@ flask_cloudflared==0.0.14
sse-starlette==1.6.5 sse-starlette==1.6.5
tiktoken tiktoken
# llama-cpp-python (CPU only, AVX2) # llama-cpp-python (CPU only)
https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.61+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/abetlen/llama-cpp-python/releases/download/v0.2.64/llama_cpp_python-0.2.64-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-0.2.61+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/abetlen/llama-cpp-python/releases/download/v0.2.64/llama_cpp_python-0.2.64-cp311-cp311-linux_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-0.2.61+cpuavx2-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11" https://github.com/abetlen/llama-cpp-python/releases/download/v0.2.64/llama_cpp_python-0.2.64-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-0.2.61+cpuavx2-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10" https://github.com/abetlen/llama-cpp-python/releases/download/v0.2.64/llama_cpp_python-0.2.64-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
# AMD wheels # AMD wheels
https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/rocm/llama_cpp_python_cuda-0.2.61+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/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/rocm/llama_cpp_python_cuda-0.2.61+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/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-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-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
https://github.com/turboderp/exllamav2/releases/download/v0.0.19/exllamav2-0.0.19+rocm5.6-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11" https://github.com/turboderp/exllamav2/releases/download/v0.0.19/exllamav2-0.0.19+rocm5.6-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"

49
requirements_amd_noavx2.txt
View File

@ -1,49 +0,0 @@
accelerate==0.27.*
colorama
datasets
einops
gradio==4.26.*
hqq==0.1.5
jinja2==3.1.2
lm_eval==0.3.0
markdown
numba==0.59.*
numpy==1.26.*
optimum==1.17.*
pandas
peft==0.8.*
Pillow>=9.5.0
psutil
pyyaml
requests
rich
safetensors==0.4.*
scipy
sentencepiece
tensorboard
transformers==4.40.*
tqdm
wandb
# API
SpeechRecognition==3.10.0
flask_cloudflared==0.0.14
sse-starlette==1.6.5
tiktoken
# llama-cpp-python (CPU only, no AVX2)
https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.61+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-0.2.61+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-0.2.61+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-0.2.61+cpuavx-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
# AMD wheels
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/turboderp/exllamav2/releases/download/v0.0.19/exllamav2-0.0.19+rocm5.6-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
https://github.com/turboderp/exllamav2/releases/download/v0.0.19/exllamav2-0.0.19+rocm5.6-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
https://github.com/turboderp/exllamav2/releases/download/v0.0.19/exllamav2-0.0.19-py3-none-any.whl; platform_system != "Darwin" and platform_machine != "x86_64"
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/casper-hansen/AutoAWQ/releases/download/v0.2.3/autoawq-0.2.3+rocm561-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
https://github.com/casper-hansen/AutoAWQ/releases/download/v0.2.3/autoawq-0.2.3+rocm561-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"

12
requirements_apple_intel.txt
View File

@ -32,10 +32,10 @@ sse-starlette==1.6.5
tiktoken tiktoken
# Mac wheels # Mac wheels
https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.61-cp311-cp311-macosx_11_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "20.0.0" and platform_release < "21.0.0" and python_version == "3.11" https://github.com/abetlen/llama-cpp-python/releases/download/v0.2.64-metal/llama_cpp_python-0.2.64-cp311-cp311-macosx_11_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "20.0.0" and platform_release < "21.0.0" and python_version == "3.11"
https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.61-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/abetlen/llama-cpp-python/releases/download/v0.2.64-metal/llama_cpp_python-0.2.64-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/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.61-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/abetlen/llama-cpp-python/releases/download/v0.2.64-metal/llama_cpp_python-0.2.64-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/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.61-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/abetlen/llama-cpp-python/releases/download/v0.2.64-metal/llama_cpp_python-0.2.64-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/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.61-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/abetlen/llama-cpp-python/releases/download/v0.2.64-metal/llama_cpp_python-0.2.64-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/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.61-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/abetlen/llama-cpp-python/releases/download/v0.2.64-metal/llama_cpp_python-0.2.64-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/turboderp/exllamav2/releases/download/v0.0.19/exllamav2-0.0.19-py3-none-any.whl https://github.com/turboderp/exllamav2/releases/download/v0.0.19/exllamav2-0.0.19-py3-none-any.whl

16
requirements_apple_silicon.txt
View File

@ -32,12 +32,12 @@ sse-starlette==1.6.5
tiktoken tiktoken
# Mac wheels # Mac wheels
https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.61-cp311-cp311-macosx_11_0_arm64.whl; platform_system == "Darwin" and platform_release >= "20.0.0" and platform_release < "21.0.0" and python_version == "3.11" https://github.com/abetlen/llama-cpp-python/releases/download/v0.2.64-metal/llama_cpp_python-0.2.64-cp311-cp311-macosx_11_0_arm64.whl; platform_system == "Darwin" and platform_release >= "20.0.0" and platform_release < "21.0.0" and python_version == "3.11"
https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.61-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/abetlen/llama-cpp-python/releases/download/v0.2.64-metal/llama_cpp_python-0.2.64-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/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.61-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/abetlen/llama-cpp-python/releases/download/v0.2.64-metal/llama_cpp_python-0.2.64-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/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.61-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/abetlen/llama-cpp-python/releases/download/v0.2.64-metal/llama_cpp_python-0.2.64-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/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.61-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/abetlen/llama-cpp-python/releases/download/v0.2.64-metal/llama_cpp_python-0.2.64-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/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.61-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/abetlen/llama-cpp-python/releases/download/v0.2.64-metal/llama_cpp_python-0.2.64-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/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.61-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/abetlen/llama-cpp-python/releases/download/v0.2.64-metal/llama_cpp_python-0.2.64-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/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.61-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/abetlen/llama-cpp-python/releases/download/v0.2.64-metal/llama_cpp_python-0.2.64-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/turboderp/exllamav2/releases/download/v0.0.19/exllamav2-0.0.19-py3-none-any.whl https://github.com/turboderp/exllamav2/releases/download/v0.0.19/exllamav2-0.0.19-py3-none-any.whl

10
requirements_cpu_only.txt
View File

@ -31,8 +31,8 @@ flask_cloudflared==0.0.14
sse-starlette==1.6.5 sse-starlette==1.6.5
tiktoken tiktoken
# llama-cpp-python (CPU only, AVX2) # llama-cpp-python (CPU only)
https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.61+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/abetlen/llama-cpp-python/releases/download/v0.2.64/llama_cpp_python-0.2.64-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-0.2.61+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/abetlen/llama-cpp-python/releases/download/v0.2.64/llama_cpp_python-0.2.64-cp311-cp311-linux_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-0.2.61+cpuavx2-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11" https://github.com/abetlen/llama-cpp-python/releases/download/v0.2.64/llama_cpp_python-0.2.64-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-0.2.61+cpuavx2-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10" https://github.com/abetlen/llama-cpp-python/releases/download/v0.2.64/llama_cpp_python-0.2.64-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"

38
requirements_cpu_only_noavx2.txt
View File

@ -1,38 +0,0 @@
accelerate==0.27.*
colorama
datasets
einops
gradio==4.26.*
hqq==0.1.5
jinja2==3.1.2
lm_eval==0.3.0
markdown
numba==0.59.*
numpy==1.26.*
optimum==1.17.*
pandas
peft==0.8.*
Pillow>=9.5.0
psutil
pyyaml
requests
rich
safetensors==0.4.*
scipy
sentencepiece
tensorboard
transformers==4.40.*
tqdm
wandb
# API
SpeechRecognition==3.10.0
flask_cloudflared==0.0.14
sse-starlette==1.6.5
tiktoken
# llama-cpp-python (CPU only, no AVX2)
https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.61+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-0.2.61+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-0.2.61+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-0.2.61+cpuavx-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"

72
requirements_noavx2.txt
View File

@ -1,72 +0,0 @@
accelerate==0.27.*
aqlm[gpu,cpu]==1.1.3; platform_system == "Linux"
bitsandbytes==0.43.*
colorama
datasets
einops
gradio==4.26.*
hqq==0.1.5
jinja2==3.1.2
lm_eval==0.3.0
markdown
numba==0.59.*
numpy==1.26.*
optimum==1.17.*
pandas
peft==0.8.*
Pillow>=9.5.0
psutil
pyyaml
requests
rich
safetensors==0.4.*
scipy
sentencepiece
tensorboard
transformers==4.40.*
tqdm
wandb
# API
SpeechRecognition==3.10.0
flask_cloudflared==0.0.14
sse-starlette==1.6.5
tiktoken
# llama-cpp-python (CPU only, no AVX2)
https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.61+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-0.2.61+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-0.2.61+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-0.2.61+cpuavx-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
# llama-cpp-python (CUDA, no tensor cores)
https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.61+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-0.2.61+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-0.2.61+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-0.2.61+cu121avx-cp310-cp310-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
# llama-cpp-python (CUDA, tensor cores)
https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda_tensorcores-0.2.61+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_tensorcores-0.2.61+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_tensorcores-0.2.61+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_tensorcores-0.2.61+cu121avx-cp310-cp310-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
# CUDA wheels
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-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/turboderp/exllamav2/releases/download/v0.0.19/exllamav2-0.0.19+cu121-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
https://github.com/turboderp/exllamav2/releases/download/v0.0.19/exllamav2-0.0.19+cu121-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
https://github.com/turboderp/exllamav2/releases/download/v0.0.19/exllamav2-0.0.19+cu121-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
https://github.com/turboderp/exllamav2/releases/download/v0.0.19/exllamav2-0.0.19+cu121-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
https://github.com/turboderp/exllamav2/releases/download/v0.0.19/exllamav2-0.0.19-py3-none-any.whl; platform_system == "Linux" and platform_machine != "x86_64"
https://github.com/oobabooga/flash-attention/releases/download/v2.5.6/flash_attn-2.5.6+cu122torch2.2.0cxx11abiFALSE-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
https://github.com/oobabooga/flash-attention/releases/download/v2.5.6/flash_attn-2.5.6+cu122torch2.2.0cxx11abiFALSE-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
https://github.com/Dao-AILab/flash-attention/releases/download/v2.5.6/flash_attn-2.5.6+cu122torch2.2cxx11abiFALSE-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
https://github.com/Dao-AILab/flash-attention/releases/download/v2.5.6/flash_attn-2.5.6+cu122torch2.2cxx11abiFALSE-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+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-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+cu121-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
autoawq==0.2.3; platform_system == "Linux" or platform_system == "Windows"