diff --git a/extensions/Training_PRO/script.py b/extensions/Training_PRO/script.py
index 8f296462..5365154c 100644
--- a/extensions/Training_PRO/script.py
+++ b/extensions/Training_PRO/script.py
@@ -241,7 +241,7 @@ def ui():
                         stride_length = gr.Slider(label='Stride', minimum=1, maximum=2048, value=512, step=1, info='Used to make the evaluation faster at the cost of accuracy. 1 = slowest but most accurate. 512 is a common value.')
 
                     with gr.Column():
-                        max_length = gr.Slider(label='max_length', minimum=0, maximum=shared.settings['truncation_length_max'], value=0, step=1, info='The context for each evaluation. If set to 0, the maximum context length for the model will be used.')
+                        max_length = gr.Number(label='max_length', precision=0, step=256, value=0, info='The context for each evaluation. If set to 0, the maximum context length for the model will be used.')
 
                 with gr.Row():
                     start_current_evaluation = gr.Button("Evaluate loaded model")
diff --git a/extensions/openai/completions.py b/extensions/openai/completions.py
index 646dee2d..6bd8f409 100644
--- a/extensions/openai/completions.py
+++ b/extensions/openai/completions.py
@@ -154,8 +154,9 @@ def convert_history(history):
                     elif item['type'] == 'text' and isinstance(item['text'], str):
                         content = item['text']
 
-                if image_url and content:
+                if image_url:
                     new_history.append({"image_url": image_url, "role": "user"})
+                if content:
                     new_history.append({"content": content, "role": "user"})
             else:
                 new_history.append(entry)
@@ -234,7 +235,7 @@ def chat_completions_common(body: dict, is_legacy: bool = False, stream=False, p
             raise InvalidRequestError(message="messages: missing content", param='messages')
 
     # Chat Completions
-    object_type = 'chat.completions' if not stream else 'chat.completions.chunk'
+    object_type = 'chat.completion' if not stream else 'chat.completion.chunk'
     created_time = int(time.time())
     cmpl_id = "chatcmpl-%d" % (int(time.time() * 1000000000))
     resp_list = 'data' if is_legacy else 'choices'
diff --git a/modules/LoRA.py b/modules/LoRA.py
index 117022cf..4fd144ba 100644
--- a/modules/LoRA.py
+++ b/modules/LoRA.py
@@ -1,7 +1,6 @@
 from pathlib import Path
 
 import torch
-from peft import PeftModel
 from transformers import is_torch_xpu_available
 
 import modules.shared as shared
@@ -85,6 +84,9 @@ def add_lora_autogptq(lora_names):
 
 
 def add_lora_transformers(lora_names):
+
+    from peft import PeftModel
+
     prior_set = set(shared.lora_names)
     added_set = set(lora_names) - prior_set
     removed_set = prior_set - set(lora_names)
diff --git a/modules/llama_cpp_python_hijack.py b/modules/llama_cpp_python_hijack.py
index 64280dc9..3d42b2d7 100644
--- a/modules/llama_cpp_python_hijack.py
+++ b/modules/llama_cpp_python_hijack.py
@@ -61,7 +61,7 @@ def eval_with_progress(self, tokens: Sequence[int]):
     assert self._batch.batch is not None
     self._ctx.kv_cache_seq_rm(-1, self.n_tokens, -1)
 
-    if len(tokens) > 1:
+    if len(tokens) > self.n_batch:
         progress_bar = tqdm(range(0, len(tokens), self.n_batch), desc="Prompt evaluation", leave=False)
     else:
         progress_bar = range(0, len(tokens), self.n_batch)
diff --git a/modules/text_generation.py b/modules/text_generation.py
index 75e5ef36..e7a2b43f 100644
--- a/modules/text_generation.py
+++ b/modules/text_generation.py
@@ -274,7 +274,12 @@ def get_reply_from_output_ids(output_ids, state=None, starting_from=0):
     if (hasattr(shared.tokenizer, 'convert_ids_to_tokens') and len(output_ids) > starting_from) and not reply.startswith(' '):
         first_token = shared.tokenizer.convert_ids_to_tokens(int(output_ids[starting_from]))
         if isinstance(first_token, (bytes,)):
-            first_token = first_token.decode('utf8')
+            #try to decode the bytes to a string
+            try:
+                first_token = first_token.decode('utf8')
+            #if it fails, which means it's not a string in this turn, just ignore it
+            except UnicodeDecodeError:
+                first_token = ''
 
         if first_token.startswith('▁'):
             reply = ' ' + reply
diff --git a/modules/training.py b/modules/training.py
index b003fc8c..11c4b8c5 100644
--- a/modules/training.py
+++ b/modules/training.py
@@ -18,14 +18,6 @@ import gradio as gr
 import torch
 import transformers
 from datasets import Dataset, load_dataset
-from peft import (
-    LoraConfig,
-    get_peft_model,
-    prepare_model_for_kbit_training,
-    set_peft_model_state_dict
-)
-from peft.utils.other import \
-    TRANSFORMERS_MODELS_TO_LORA_TARGET_MODULES_MAPPING as model_to_lora_modules
 from transformers import is_torch_xpu_available
 from transformers.models.auto.modeling_auto import (
     MODEL_FOR_CAUSAL_LM_MAPPING_NAMES
@@ -292,6 +284,16 @@ def calc_trainable_parameters(model):
 
 def do_train(lora_name: str, always_override: bool, q_proj_en: bool, v_proj_en: bool, k_proj_en: bool, o_proj_en: bool, gate_proj_en: bool, down_proj_en: bool, up_proj_en: bool, save_steps: int, micro_batch_size: int, batch_size: int, epochs: int, learning_rate: str, lr_scheduler_type: str, lora_rank: int, lora_alpha: int, lora_dropout: float, cutoff_len: int, dataset: str, eval_dataset: str, format: str, eval_steps: int, raw_text_file: str, overlap_len: int, newline_favor_len: int, higher_rank_limit: bool, warmup_steps: int, optimizer: str, hard_cut_string: str, train_only_after: str, stop_at_loss: float, add_eos_token: bool, min_chars: int, report_to: str):
 
+    from peft import (
+        LoraConfig,
+        get_peft_model,
+        prepare_model_for_kbit_training,
+        set_peft_model_state_dict
+    )
+    from peft.utils.other import \
+        TRANSFORMERS_MODELS_TO_LORA_TARGET_MODULES_MAPPING as \
+        model_to_lora_modules
+
     global WANT_INTERRUPT
     WANT_INTERRUPT = False
 
diff --git a/requirements.txt b/requirements.txt
index 9c8ffd94..8ad08659 100644
--- a/requirements.txt
+++ b/requirements.txt
@@ -5,6 +5,7 @@ bitsandbytes==0.43.*
 colorama
 datasets
 einops
+fastapi==0.112.4
 gradio==4.26.*
 hqq==0.1.7.post3
 jinja2==3.1.4
@@ -17,6 +18,7 @@ pandas
 peft==0.12.*
 Pillow>=9.5.0
 psutil
+pydantic==2.8.2
 pyyaml
 requests
 rich
@@ -37,33 +39,33 @@ soundfile
 openai-whisper
 
 # llama-cpp-python (CPU only, AVX2)
-https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.89+cpuavx2-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-0.2.89+cpuavx2-cp310-cp310-linux_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-0.2.89+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-0.2.89+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-0.2.90+cpuavx2-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-0.2.90+cpuavx2-cp310-cp310-linux_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-0.2.90+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-0.2.90+cpuavx2-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-0.2.89+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-0.2.89+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-0.2.89+cu121-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/textgen-webui/llama_cpp_python_cuda-0.2.89+cu121-cp310-cp310-linux_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-0.2.90+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-0.2.90+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-0.2.90+cu121-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/textgen-webui/llama_cpp_python_cuda-0.2.90+cu121-cp310-cp310-linux_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-0.2.89+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-0.2.89+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-0.2.89+cu121-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/textgen-webui/llama_cpp_python_cuda_tensorcores-0.2.89+cu121-cp310-cp310-linux_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_tensorcores-0.2.90+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-0.2.90+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-0.2.90+cu121-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/textgen-webui/llama_cpp_python_cuda_tensorcores-0.2.90+cu121-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
 
 # CUDA wheels
-https://github.com/oobabooga/exllamav2/releases/download/v0.1.9/exllamav2-0.1.9+cu121.torch2.2.2-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
-https://github.com/oobabooga/exllamav2/releases/download/v0.1.9/exllamav2-0.1.9+cu121.torch2.2.2-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
-https://github.com/oobabooga/exllamav2/releases/download/v0.1.9/exllamav2-0.1.9+cu121.torch2.2.2-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
-https://github.com/oobabooga/exllamav2/releases/download/v0.1.9/exllamav2-0.1.9+cu121.torch2.2.2-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
-https://github.com/oobabooga/exllamav2/releases/download/v0.1.9/exllamav2-0.1.9-py3-none-any.whl; platform_system == "Linux" and platform_machine != "x86_64"
-https://github.com/oobabooga/flash-attention/releases/download/v2.6.1/flash_attn-2.6.1+cu122torch2.2.2cxx11abiFALSE-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
-https://github.com/oobabooga/flash-attention/releases/download/v2.6.1/flash_attn-2.6.1+cu122torch2.2.2cxx11abiFALSE-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
-https://github.com/Dao-AILab/flash-attention/releases/download/v2.6.1/flash_attn-2.6.1+cu123torch2.2cxx11abiFALSE-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/v2.6.1/flash_attn-2.6.1+cu123torch2.2cxx11abiFALSE-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
+https://github.com/oobabooga/exllamav2/releases/download/v0.2.0/exllamav2-0.2.0+cu121.torch2.2.2-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
+https://github.com/oobabooga/exllamav2/releases/download/v0.2.0/exllamav2-0.2.0+cu121.torch2.2.2-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
+https://github.com/oobabooga/exllamav2/releases/download/v0.2.0/exllamav2-0.2.0+cu121.torch2.2.2-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
+https://github.com/oobabooga/exllamav2/releases/download/v0.2.0/exllamav2-0.2.0+cu121.torch2.2.2-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
+https://github.com/oobabooga/exllamav2/releases/download/v0.2.0/exllamav2-0.2.0-py3-none-any.whl; platform_system == "Linux" and platform_machine != "x86_64"
+https://github.com/oobabooga/flash-attention/releases/download/v2.6.3/flash_attn-2.6.3+cu122torch2.2.2cxx11abiFALSE-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
+https://github.com/oobabooga/flash-attention/releases/download/v2.6.3/flash_attn-2.6.3+cu122torch2.2.2cxx11abiFALSE-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
+https://github.com/Dao-AILab/flash-attention/releases/download/v2.6.3/flash_attn-2.6.3+cu123torch2.2cxx11abiFALSE-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/v2.6.3/flash_attn-2.6.3+cu123torch2.2cxx11abiFALSE-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
 https://github.com/oobabooga/AutoAWQ/releases/download/0.2.6/autoawq-0.2.6-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
 https://github.com/oobabooga/AutoAWQ/releases/download/0.2.6/autoawq-0.2.6-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
 https://github.com/oobabooga/AutoAWQ/releases/download/0.2.6/autoawq-0.2.6-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
@@ -71,4 +73,4 @@ https://github.com/oobabooga/AutoAWQ/releases/download/0.2.6/autoawq-0.2.6-cp310
 https://github.com/oobabooga/AutoAWQ_kernels/releases/download/0.0.7/autoawq_kernels-0.0.7-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
 https://github.com/oobabooga/AutoAWQ_kernels/releases/download/0.0.7/autoawq_kernels-0.0.7-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
 https://github.com/oobabooga/AutoAWQ_kernels/releases/download/0.0.7/autoawq_kernels-0.0.7-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
-https://github.com/oobabooga/AutoAWQ_kernels/releases/download/0.0.7/autoawq_kernels-0.0.7-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
\ No newline at end of file
+https://github.com/oobabooga/AutoAWQ_kernels/releases/download/0.0.7/autoawq_kernels-0.0.7-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
diff --git a/requirements_amd.txt b/requirements_amd.txt
index 5ff86863..20ba9c79 100644
--- a/requirements_amd.txt
+++ b/requirements_amd.txt
@@ -2,6 +2,7 @@ accelerate==0.33.*
 colorama
 datasets
 einops
+fastapi==0.112.4
 gradio==4.26.*
 hqq==0.1.7.post3
 jinja2==3.1.4
@@ -14,6 +15,7 @@ pandas
 peft==0.12.*
 Pillow>=9.5.0
 psutil
+pydantic==2.8.2
 pyyaml
 requests
 rich
@@ -32,18 +34,18 @@ sse-starlette==1.6.5
 tiktoken
 
 # llama-cpp-python (CPU only, AVX2)
-https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.89+cpuavx2-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-0.2.89+cpuavx2-cp310-cp310-linux_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-0.2.89+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-0.2.89+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-0.2.90+cpuavx2-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-0.2.90+cpuavx2-cp310-cp310-linux_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-0.2.90+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-0.2.90+cpuavx2-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
 
 # AMD wheels
-https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/rocm/llama_cpp_python_cuda-0.2.89+rocm5.6.1-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/rocm/llama_cpp_python_cuda-0.2.89+rocm5.6.1-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
-https://github.com/oobabooga/exllamav2/releases/download/v0.1.9/exllamav2-0.1.9+rocm5.6.torch2.2.2-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
-https://github.com/oobabooga/exllamav2/releases/download/v0.1.9/exllamav2-0.1.9+rocm5.6.torch2.2.2-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
-https://github.com/oobabooga/exllamav2/releases/download/v0.1.9/exllamav2-0.1.9-py3-none-any.whl; platform_system != "Darwin" and platform_machine != "x86_64"
+https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/rocm/llama_cpp_python_cuda-0.2.90+rocm5.6.1-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/rocm/llama_cpp_python_cuda-0.2.90+rocm5.6.1-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
+https://github.com/oobabooga/exllamav2/releases/download/v0.2.0/exllamav2-0.2.0+rocm5.6.torch2.2.2-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
+https://github.com/oobabooga/exllamav2/releases/download/v0.2.0/exllamav2-0.2.0+rocm5.6.torch2.2.2-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
+https://github.com/oobabooga/exllamav2/releases/download/v0.2.0/exllamav2-0.2.0-py3-none-any.whl; platform_system != "Darwin" and platform_machine != "x86_64"
 https://github.com/oobabooga/AutoAWQ/releases/download/0.2.6/autoawq-0.2.6-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
 https://github.com/oobabooga/AutoAWQ/releases/download/0.2.6/autoawq-0.2.6-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
 https://github.com/oobabooga/AutoAWQ_kernels/releases/download/0.0.7/autoawq_kernels-0.0.7+rocm561-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
-https://github.com/oobabooga/AutoAWQ_kernels/releases/download/0.0.7/autoawq_kernels-0.0.7+rocm561-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
\ No newline at end of file
+https://github.com/oobabooga/AutoAWQ_kernels/releases/download/0.0.7/autoawq_kernels-0.0.7+rocm561-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
diff --git a/requirements_amd_noavx2.txt b/requirements_amd_noavx2.txt
index c0d094e8..e5c18681 100644
--- a/requirements_amd_noavx2.txt
+++ b/requirements_amd_noavx2.txt
@@ -2,6 +2,7 @@ accelerate==0.33.*
 colorama
 datasets
 einops
+fastapi==0.112.4
 gradio==4.26.*
 hqq==0.1.7.post3
 jinja2==3.1.4
@@ -14,6 +15,7 @@ pandas
 peft==0.12.*
 Pillow>=9.5.0
 psutil
+pydantic==2.8.2
 pyyaml
 requests
 rich
@@ -32,16 +34,16 @@ 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-0.2.89+cpuavx-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-0.2.89+cpuavx-cp310-cp310-linux_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-0.2.89+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-0.2.89+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-0.2.90+cpuavx-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-0.2.90+cpuavx-cp310-cp310-linux_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-0.2.90+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-0.2.90+cpuavx-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
 
 # AMD wheels
-https://github.com/oobabooga/exllamav2/releases/download/v0.1.9/exllamav2-0.1.9+rocm5.6.torch2.2.2-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
-https://github.com/oobabooga/exllamav2/releases/download/v0.1.9/exllamav2-0.1.9+rocm5.6.torch2.2.2-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
-https://github.com/oobabooga/exllamav2/releases/download/v0.1.9/exllamav2-0.1.9-py3-none-any.whl; platform_system != "Darwin" and platform_machine != "x86_64"
+https://github.com/oobabooga/exllamav2/releases/download/v0.2.0/exllamav2-0.2.0+rocm5.6.torch2.2.2-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
+https://github.com/oobabooga/exllamav2/releases/download/v0.2.0/exllamav2-0.2.0+rocm5.6.torch2.2.2-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
+https://github.com/oobabooga/exllamav2/releases/download/v0.2.0/exllamav2-0.2.0-py3-none-any.whl; platform_system != "Darwin" and platform_machine != "x86_64"
 https://github.com/oobabooga/AutoAWQ/releases/download/0.2.6/autoawq-0.2.6-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
 https://github.com/oobabooga/AutoAWQ/releases/download/0.2.6/autoawq-0.2.6-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
 https://github.com/oobabooga/AutoAWQ_kernels/releases/download/0.0.7/autoawq_kernels-0.0.7+rocm561-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
-https://github.com/oobabooga/AutoAWQ_kernels/releases/download/0.0.7/autoawq_kernels-0.0.7+rocm561-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
\ No newline at end of file
+https://github.com/oobabooga/AutoAWQ_kernels/releases/download/0.0.7/autoawq_kernels-0.0.7+rocm561-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
diff --git a/requirements_apple_intel.txt b/requirements_apple_intel.txt
index cbcf1175..e60937c7 100644
--- a/requirements_apple_intel.txt
+++ b/requirements_apple_intel.txt
@@ -2,6 +2,7 @@ accelerate==0.33.*
 colorama
 datasets
 einops
+fastapi==0.112.4
 gradio==4.26.*
 hqq==0.1.7.post3
 jinja2==3.1.4
@@ -14,6 +15,7 @@ pandas
 peft==0.12.*
 Pillow>=9.5.0
 psutil
+pydantic==2.8.2
 pyyaml
 requests
 rich
@@ -32,8 +34,8 @@ sse-starlette==1.6.5
 tiktoken
 
 # Mac wheels
-https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.89-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-0.2.89-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-0.2.89-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-0.2.89-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/oobabooga/exllamav2/releases/download/v0.1.9/exllamav2-0.1.9-py3-none-any.whl
+https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.90-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-0.2.90-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-0.2.90-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-0.2.90-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/oobabooga/exllamav2/releases/download/v0.2.0/exllamav2-0.2.0-py3-none-any.whl
diff --git a/requirements_apple_silicon.txt b/requirements_apple_silicon.txt
index d5cb3675..e1b726bb 100644
--- a/requirements_apple_silicon.txt
+++ b/requirements_apple_silicon.txt
@@ -2,6 +2,7 @@ accelerate==0.33.*
 colorama
 datasets
 einops
+fastapi==0.112.4
 gradio==4.26.*
 hqq==0.1.7.post3
 jinja2==3.1.4
@@ -14,6 +15,7 @@ pandas
 peft==0.12.*
 Pillow>=9.5.0
 psutil
+pydantic==2.8.2
 pyyaml
 requests
 rich
@@ -32,10 +34,10 @@ sse-starlette==1.6.5
 tiktoken
 
 # Mac wheels
-https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.89-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-0.2.89-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-0.2.89-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-0.2.89-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-0.2.89-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-0.2.89-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/oobabooga/exllamav2/releases/download/v0.1.9/exllamav2-0.1.9-py3-none-any.whl
+https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.90-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-0.2.90-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-0.2.90-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-0.2.90-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-0.2.90-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-0.2.90-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/oobabooga/exllamav2/releases/download/v0.2.0/exllamav2-0.2.0-py3-none-any.whl
diff --git a/requirements_cpu_only.txt b/requirements_cpu_only.txt
index 807c182a..b0480c43 100644
--- a/requirements_cpu_only.txt
+++ b/requirements_cpu_only.txt
@@ -2,6 +2,7 @@ accelerate==0.33.*
 colorama
 datasets
 einops
+fastapi==0.112.4
 gradio==4.26.*
 hqq==0.1.7.post3
 jinja2==3.1.4
@@ -14,6 +15,7 @@ pandas
 peft==0.12.*
 Pillow>=9.5.0
 psutil
+pydantic==2.8.2
 pyyaml
 requests
 rich
@@ -32,7 +34,7 @@ sse-starlette==1.6.5
 tiktoken
 
 # llama-cpp-python (CPU only, AVX2)
-https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.89+cpuavx2-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-0.2.89+cpuavx2-cp310-cp310-linux_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-0.2.89+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-0.2.89+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-0.2.90+cpuavx2-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-0.2.90+cpuavx2-cp310-cp310-linux_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-0.2.90+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-0.2.90+cpuavx2-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
diff --git a/requirements_cpu_only_noavx2.txt b/requirements_cpu_only_noavx2.txt
index e2a89936..a64d68a7 100644
--- a/requirements_cpu_only_noavx2.txt
+++ b/requirements_cpu_only_noavx2.txt
@@ -2,6 +2,7 @@ accelerate==0.33.*
 colorama
 datasets
 einops
+fastapi==0.112.4
 gradio==4.26.*
 hqq==0.1.7.post3
 jinja2==3.1.4
@@ -14,6 +15,7 @@ pandas
 peft==0.12.*
 Pillow>=9.5.0
 psutil
+pydantic==2.8.2
 pyyaml
 requests
 rich
@@ -32,7 +34,7 @@ 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-0.2.89+cpuavx-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-0.2.89+cpuavx-cp310-cp310-linux_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-0.2.89+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-0.2.89+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-0.2.90+cpuavx-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-0.2.90+cpuavx-cp310-cp310-linux_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-0.2.90+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-0.2.90+cpuavx-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
diff --git a/requirements_noavx2.txt b/requirements_noavx2.txt
index bfe57329..cae98bb2 100644
--- a/requirements_noavx2.txt
+++ b/requirements_noavx2.txt
@@ -5,6 +5,7 @@ bitsandbytes==0.43.*
 colorama
 datasets
 einops
+fastapi==0.112.4
 gradio==4.26.*
 hqq==0.1.7.post3
 jinja2==3.1.4
@@ -17,6 +18,7 @@ pandas
 peft==0.12.*
 Pillow>=9.5.0
 psutil
+pydantic==2.8.2
 pyyaml
 requests
 rich
@@ -35,33 +37,33 @@ 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-0.2.89+cpuavx-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-0.2.89+cpuavx-cp310-cp310-linux_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-0.2.89+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-0.2.89+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-0.2.90+cpuavx-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-0.2.90+cpuavx-cp310-cp310-linux_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-0.2.90+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-0.2.90+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-0.2.89+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-0.2.89+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-0.2.89+cu121avx-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/textgen-webui/llama_cpp_python_cuda-0.2.89+cu121avx-cp310-cp310-linux_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-0.2.90+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-0.2.90+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-0.2.90+cu121avx-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/textgen-webui/llama_cpp_python_cuda-0.2.90+cu121avx-cp310-cp310-linux_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-0.2.89+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-0.2.89+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-0.2.89+cu121avx-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/textgen-webui/llama_cpp_python_cuda_tensorcores-0.2.89+cu121avx-cp310-cp310-linux_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_tensorcores-0.2.90+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-0.2.90+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-0.2.90+cu121avx-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/textgen-webui/llama_cpp_python_cuda_tensorcores-0.2.90+cu121avx-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
 
 # CUDA wheels
-https://github.com/oobabooga/exllamav2/releases/download/v0.1.9/exllamav2-0.1.9+cu121.torch2.2.2-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
-https://github.com/oobabooga/exllamav2/releases/download/v0.1.9/exllamav2-0.1.9+cu121.torch2.2.2-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
-https://github.com/oobabooga/exllamav2/releases/download/v0.1.9/exllamav2-0.1.9+cu121.torch2.2.2-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
-https://github.com/oobabooga/exllamav2/releases/download/v0.1.9/exllamav2-0.1.9+cu121.torch2.2.2-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
-https://github.com/oobabooga/exllamav2/releases/download/v0.1.9/exllamav2-0.1.9-py3-none-any.whl; platform_system == "Linux" and platform_machine != "x86_64"
-https://github.com/oobabooga/flash-attention/releases/download/v2.6.1/flash_attn-2.6.1+cu122torch2.2.2cxx11abiFALSE-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
-https://github.com/oobabooga/flash-attention/releases/download/v2.6.1/flash_attn-2.6.1+cu122torch2.2.2cxx11abiFALSE-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
-https://github.com/Dao-AILab/flash-attention/releases/download/v2.6.1/flash_attn-2.6.1+cu123torch2.2cxx11abiFALSE-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/v2.6.1/flash_attn-2.6.1+cu123torch2.2cxx11abiFALSE-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
+https://github.com/oobabooga/exllamav2/releases/download/v0.2.0/exllamav2-0.2.0+cu121.torch2.2.2-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
+https://github.com/oobabooga/exllamav2/releases/download/v0.2.0/exllamav2-0.2.0+cu121.torch2.2.2-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
+https://github.com/oobabooga/exllamav2/releases/download/v0.2.0/exllamav2-0.2.0+cu121.torch2.2.2-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
+https://github.com/oobabooga/exllamav2/releases/download/v0.2.0/exllamav2-0.2.0+cu121.torch2.2.2-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
+https://github.com/oobabooga/exllamav2/releases/download/v0.2.0/exllamav2-0.2.0-py3-none-any.whl; platform_system == "Linux" and platform_machine != "x86_64"
+https://github.com/oobabooga/flash-attention/releases/download/v2.6.3/flash_attn-2.6.3+cu122torch2.2.2cxx11abiFALSE-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
+https://github.com/oobabooga/flash-attention/releases/download/v2.6.3/flash_attn-2.6.3+cu122torch2.2.2cxx11abiFALSE-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
+https://github.com/Dao-AILab/flash-attention/releases/download/v2.6.3/flash_attn-2.6.3+cu123torch2.2cxx11abiFALSE-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/v2.6.3/flash_attn-2.6.3+cu123torch2.2cxx11abiFALSE-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
 https://github.com/oobabooga/AutoAWQ/releases/download/0.2.6/autoawq-0.2.6-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
 https://github.com/oobabooga/AutoAWQ/releases/download/0.2.6/autoawq-0.2.6-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
 https://github.com/oobabooga/AutoAWQ/releases/download/0.2.6/autoawq-0.2.6-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
@@ -69,4 +71,4 @@ https://github.com/oobabooga/AutoAWQ/releases/download/0.2.6/autoawq-0.2.6-cp310
 https://github.com/oobabooga/AutoAWQ_kernels/releases/download/0.0.7/autoawq_kernels-0.0.7-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
 https://github.com/oobabooga/AutoAWQ_kernels/releases/download/0.0.7/autoawq_kernels-0.0.7-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
 https://github.com/oobabooga/AutoAWQ_kernels/releases/download/0.0.7/autoawq_kernels-0.0.7-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
-https://github.com/oobabooga/AutoAWQ_kernels/releases/download/0.0.7/autoawq_kernels-0.0.7-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
\ No newline at end of file
+https://github.com/oobabooga/AutoAWQ_kernels/releases/download/0.0.7/autoawq_kernels-0.0.7-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
diff --git a/requirements_nowheels.txt b/requirements_nowheels.txt
index ffb45fe3..ec18464d 100644
--- a/requirements_nowheels.txt
+++ b/requirements_nowheels.txt
@@ -2,6 +2,7 @@ accelerate==0.33.*
 colorama
 datasets
 einops
+fastapi==0.112.4
 gradio==4.26.*
 hqq==0.1.7.post3
 jinja2==3.1.4
@@ -14,6 +15,7 @@ pandas
 peft==0.12.*
 Pillow>=9.5.0
 psutil
+pydantic==2.8.2
 pyyaml
 requests
 rich