oobabooga/text-generation-webui
1
0
Fork 0
mirror of https://github.com/oobabooga/text-generation-webui.git synced 2026-01-27 02:44:49 +01:00
Code Issues Actions Packages Projects Releases Wiki Activity

Merge pull request #7181 from oobabooga/dev

Browse source 
Merge dev branch
This commit is contained in:
oobabooga 2025-08-07 00:30:46 -03:00 committed by GitHub
parent fefdb20f69 f1147c9926
commit 88ba4b1ebf
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
19 changed files with 121 additions and 52 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

97
modules/chat.py
View file

@ -211,7 +211,57 @@ def generate_chat_prompt(user_input, state, **kwargs):
messages.insert(insert_pos, {"role": "tool", "content": tool_msg})
if assistant_msg:
messages.insert(insert_pos, {"role": "assistant", "content": assistant_msg})
# Handle GPT-OSS as a special case
if '<|channel|>analysis<|message|>' in assistant_msg or '<|channel|>final<|message|>' in assistant_msg:
thinking_content = ""
final_content = ""
# Extract analysis content if present
if '<|channel|>analysis<|message|>' in assistant_msg:
# Split the message by the analysis tag to isolate the content that follows
parts = assistant_msg.split('<|channel|>analysis<|message|>', 1)
if len(parts) > 1:
# The content is everything after the tag
potential_content = parts[1]
# Now, find the end of this content block
analysis_end_tag = '<|end|>'
if analysis_end_tag in potential_content:
thinking_content = potential_content.split(analysis_end_tag, 1)[0].strip()
else:
# Fallback: if no <|end|> tag, stop at the start of the final channel if it exists
final_channel_tag = '<|channel|>final<|message|>'
if final_channel_tag in potential_content:
thinking_content = potential_content.split(final_channel_tag, 1)[0].strip()
else:
thinking_content = potential_content.strip()
# Extract final content if present
final_tag_to_find = '<|channel|>final<|message|>'
if final_tag_to_find in assistant_msg:
# Split the message by the final tag to isolate the content that follows
parts = assistant_msg.split(final_tag_to_find, 1)
if len(parts) > 1:
# The content is everything after the tag
potential_content = parts[1]
# Now, find the end of this content block
final_end_tag = '<|end|>'
if final_end_tag in potential_content:
final_content = potential_content.split(final_end_tag, 1)[0].strip()
else:
final_content = potential_content.strip()
# Insert as structured message
msg_dict = {"role": "assistant", "content": final_content}
if '<|channel|>analysis<|message|>' in assistant_msg:
msg_dict["thinking"] = thinking_content
messages.insert(insert_pos, msg_dict)
else:
messages.insert(insert_pos, {"role": "assistant", "content": assistant_msg})
if user_msg not in ['', '<|BEGIN-VISIBLE-CHAT|>']:
# Check for user message attachments in metadata
@ -296,23 +346,42 @@ def generate_chat_prompt(user_input, state, **kwargs):
if len(suffix) > 0:
prompt = prompt[:-len(suffix)]
else:
if _continue:
suffix = get_generation_prompt(renderer, impersonate=impersonate)[1]
if len(suffix) > 0:
prompt = prompt[:-len(suffix)]
# Handle GPT-OSS as a special case when continuing
if _continue and '<|channel|>final<|message|>' in state['instruction_template_str']:
last_message_to_continue = messages[-1]
prompt = renderer(messages=messages[:-1])
# Start the assistant turn wrapper
assistant_reply_so_far = "<|start|>assistant"
if 'thinking' in last_message_to_continue:
assistant_reply_so_far += f"<|channel|>analysis<|message|>{last_message_to_continue['thinking']}<|end|>"
assistant_reply_so_far += f"<|channel|>final<|message|>{last_message_to_continue.get('content', '')}"
prompt += assistant_reply_so_far
else:
prefix = get_generation_prompt(renderer, impersonate=impersonate)[0]
prompt = renderer(messages=messages)
if _continue:
suffix = get_generation_prompt(renderer, impersonate=impersonate)[1]
if len(suffix) > 0:
prompt = prompt[:-len(suffix)]
else:
prefix = get_generation_prompt(renderer, impersonate=impersonate)[0]
# Handle GPT-OSS as a special case
if '<|channel|>final<|message|>' in state['instruction_template_str']:
prefix = prefix.rstrip("<|channel|>final<|message|>")
if impersonate:
prefix += "<|message|>"
# Handle GPT-OSS as a special case when not continuing
if '<|channel|>final<|message|>' in state['instruction_template_str']:
if prefix.endswith("<|channel|>final<|message|>"):
prefix = prefix[:-len("<|channel|>final<|message|>")]
if state['mode'] == 'chat' and not impersonate:
prefix = apply_extensions('bot_prefix', prefix, state)
if impersonate:
prefix += "<|message|>"
prompt += prefix
if state['mode'] == 'chat' and not impersonate:
prefix = apply_extensions('bot_prefix', prefix, state)
prompt += prefix
if state['mode'] == 'instruct' and 'enable_thinking' in state['instruction_template_str'] and not any((_continue, impersonate, state['enable_thinking'])):
prompt += get_thinking_suppression_string(instruction_template)

4
requirements/full/requirements.txt
View file

@ -34,8 +34,8 @@ sse-starlette==1.6.5
tiktoken
# CUDA wheels
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.32.0/llama_cpp_binaries-0.32.0+cu124-py3-none-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.32.0/llama_cpp_binaries-0.32.0+cu124-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.33.0/llama_cpp_binaries-0.33.0+cu124-py3-none-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.33.0/llama_cpp_binaries-0.33.0+cu124-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
https://github.com/oobabooga/exllamav3/releases/download/v0.0.5/exllamav3-0.0.5+cu124.torch2.6.0-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
https://github.com/oobabooga/exllamav3/releases/download/v0.0.5/exllamav3-0.0.5+cu124.torch2.6.0-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
https://github.com/turboderp-org/exllamav2/releases/download/v0.3.2/exllamav2-0.3.2+cu124.torch2.6.0-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"

4
requirements/full/requirements_amd.txt
View file

@ -33,7 +33,7 @@ sse-starlette==1.6.5
tiktoken
# AMD wheels
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.32.0/llama_cpp_binaries-0.32.0+vulkan-py3-none-win_amd64.whl; platform_system == "Windows"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.32.0/llama_cpp_binaries-0.32.0+vulkan-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.33.0/llama_cpp_binaries-0.33.0+vulkan-py3-none-win_amd64.whl; platform_system == "Windows"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.33.0/llama_cpp_binaries-0.33.0+vulkan-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
https://github.com/turboderp-org/exllamav2/releases/download/v0.3.2/exllamav2-0.3.2+rocm6.2.4.torch2.6.0-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
https://github.com/turboderp-org/exllamav2/releases/download/v0.3.2/exllamav2-0.3.2-py3-none-any.whl; platform_system != "Darwin" and platform_machine != "x86_64"

4
requirements/full/requirements_amd_noavx2.txt
View file

@ -33,7 +33,7 @@ sse-starlette==1.6.5
tiktoken
# AMD wheels
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.32.0/llama_cpp_binaries-0.32.0+vulkanavx-py3-none-win_amd64.whl; platform_system == "Windows"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.32.0/llama_cpp_binaries-0.32.0+vulkanavx-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.33.0/llama_cpp_binaries-0.33.0+vulkanavx-py3-none-win_amd64.whl; platform_system == "Windows"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.33.0/llama_cpp_binaries-0.33.0+vulkanavx-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
https://github.com/turboderp-org/exllamav2/releases/download/v0.3.2/exllamav2-0.3.2+rocm6.2.4.torch2.6.0-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
https://github.com/turboderp-org/exllamav2/releases/download/v0.3.2/exllamav2-0.3.2-py3-none-any.whl; platform_system != "Darwin" and platform_machine != "x86_64"

4
requirements/full/requirements_apple_intel.txt
View file

@ -33,7 +33,7 @@ sse-starlette==1.6.5
tiktoken
# Mac wheels
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.32.0/llama_cpp_binaries-0.32.0-py3-none-macosx_15_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "24.0.0" and platform_release < "25.0.0" and python_version == "3.11"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.32.0/llama_cpp_binaries-0.32.0-py3-none-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-binaries/releases/download/v0.33.0/llama_cpp_binaries-0.33.0-py3-none-macosx_15_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "24.0.0" and platform_release < "25.0.0" and python_version == "3.11"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.33.0/llama_cpp_binaries-0.33.0-py3-none-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/exllamav3/releases/download/v0.0.5/exllamav3-0.0.5-py3-none-any.whl
https://github.com/turboderp-org/exllamav2/releases/download/v0.3.2/exllamav2-0.3.2-py3-none-any.whl

6
requirements/full/requirements_apple_silicon.txt
View file

@ -33,8 +33,8 @@ sse-starlette==1.6.5
tiktoken
# Mac wheels
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.32.0/llama_cpp_binaries-0.32.0-py3-none-macosx_15_0_arm64.whl; platform_system == "Darwin" and platform_release >= "24.0.0" and platform_release < "25.0.0" and python_version == "3.11"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.32.0/llama_cpp_binaries-0.32.0-py3-none-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-binaries/releases/download/v0.32.0/llama_cpp_binaries-0.32.0-py3-none-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-binaries/releases/download/v0.33.0/llama_cpp_binaries-0.33.0-py3-none-macosx_15_0_arm64.whl; platform_system == "Darwin" and platform_release >= "24.0.0" and platform_release < "25.0.0" and python_version == "3.11"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.33.0/llama_cpp_binaries-0.33.0-py3-none-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-binaries/releases/download/v0.33.0/llama_cpp_binaries-0.33.0-py3-none-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/exllamav3/releases/download/v0.0.5/exllamav3-0.0.5-py3-none-any.whl
https://github.com/turboderp-org/exllamav2/releases/download/v0.3.2/exllamav2-0.3.2-py3-none-any.whl

4
requirements/full/requirements_cpu_only.txt
View file

@ -33,5 +33,5 @@ sse-starlette==1.6.5
tiktoken
# llama.cpp (CPU only, AVX2)
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.32.0/llama_cpp_binaries-0.32.0+cpuavx2-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.32.0/llama_cpp_binaries-0.32.0+cpuavx2-py3-none-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.33.0/llama_cpp_binaries-0.33.0+cpuavx2-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.33.0/llama_cpp_binaries-0.33.0+cpuavx2-py3-none-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"

4
requirements/full/requirements_cpu_only_noavx2.txt
View file

@ -33,5 +33,5 @@ sse-starlette==1.6.5
tiktoken
# llama.cpp (CPU only, no AVX2)
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.32.0/llama_cpp_binaries-0.32.0+cpuavx-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.32.0/llama_cpp_binaries-0.32.0+cpuavx-py3-none-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.33.0/llama_cpp_binaries-0.33.0+cpuavx-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.33.0/llama_cpp_binaries-0.33.0+cpuavx-py3-none-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"

4
requirements/full/requirements_cuda128.txt
View file

@ -34,8 +34,8 @@ sse-starlette==1.6.5
tiktoken
# CUDA wheels
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.32.0/llama_cpp_binaries-0.32.0+cu124-py3-none-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.32.0/llama_cpp_binaries-0.32.0+cu124-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.33.0/llama_cpp_binaries-0.33.0+cu124-py3-none-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.33.0/llama_cpp_binaries-0.33.0+cu124-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
https://github.com/turboderp-org/exllamav3/releases/download/v0.0.5/exllamav3-0.0.5+cu128.torch2.7.0-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
https://github.com/turboderp-org/exllamav3/releases/download/v0.0.5/exllamav3-0.0.5+cu128.torch2.7.0-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
https://github.com/turboderp-org/exllamav2/releases/download/v0.3.2/exllamav2-0.3.2+cu128.torch2.7.0-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"

4
requirements/full/requirements_cuda128_noavx2.txt
View file

@ -34,8 +34,8 @@ sse-starlette==1.6.5
tiktoken
# CUDA wheels
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.32.0/llama_cpp_binaries-0.32.0+cu124avx-py3-none-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.32.0/llama_cpp_binaries-0.32.0+cu124avx-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.33.0/llama_cpp_binaries-0.33.0+cu124avx-py3-none-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.33.0/llama_cpp_binaries-0.33.0+cu124avx-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
https://github.com/turboderp-org/exllamav3/releases/download/v0.0.5/exllamav3-0.0.5+cu128.torch2.7.0-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
https://github.com/turboderp-org/exllamav3/releases/download/v0.0.5/exllamav3-0.0.5+cu128.torch2.7.0-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
https://github.com/turboderp-org/exllamav2/releases/download/v0.3.2/exllamav2-0.3.2+cu128.torch2.7.0-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"

4
requirements/full/requirements_noavx2.txt
View file

@ -34,8 +34,8 @@ sse-starlette==1.6.5
tiktoken
# CUDA wheels
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.32.0/llama_cpp_binaries-0.32.0+cu124avx-py3-none-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.32.0/llama_cpp_binaries-0.32.0+cu124avx-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.33.0/llama_cpp_binaries-0.33.0+cu124avx-py3-none-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.33.0/llama_cpp_binaries-0.33.0+cu124avx-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
https://github.com/oobabooga/exllamav3/releases/download/v0.0.5/exllamav3-0.0.5+cu124.torch2.6.0-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
https://github.com/oobabooga/exllamav3/releases/download/v0.0.5/exllamav3-0.0.5+cu124.torch2.6.0-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
https://github.com/turboderp-org/exllamav2/releases/download/v0.3.2/exllamav2-0.3.2+cu124.torch2.6.0-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"

4
requirements/portable/requirements.txt
View file

@ -18,5 +18,5 @@ sse-starlette==1.6.5
tiktoken
# CUDA wheels
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.32.0/llama_cpp_binaries-0.32.0+cu124-py3-none-win_amd64.whl; platform_system == "Windows"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.32.0/llama_cpp_binaries-0.32.0+cu124-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.33.0/llama_cpp_binaries-0.33.0+cu124-py3-none-win_amd64.whl; platform_system == "Windows"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.33.0/llama_cpp_binaries-0.33.0+cu124-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"

4
requirements/portable/requirements_apple_intel.txt
View file

@ -18,5 +18,5 @@ sse-starlette==1.6.5
tiktoken
# Mac wheels
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.32.0/llama_cpp_binaries-0.32.0-py3-none-macosx_15_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "24.0.0" and platform_release < "25.0.0"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.32.0/llama_cpp_binaries-0.32.0-py3-none-macosx_14_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "23.0.0" and platform_release < "24.0.0"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.33.0/llama_cpp_binaries-0.33.0-py3-none-macosx_15_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "24.0.0" and platform_release < "25.0.0"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.33.0/llama_cpp_binaries-0.33.0-py3-none-macosx_14_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "23.0.0" and platform_release < "24.0.0"

6
requirements/portable/requirements_apple_silicon.txt
View file

@ -18,6 +18,6 @@ sse-starlette==1.6.5
tiktoken
# Mac wheels
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.32.0/llama_cpp_binaries-0.32.0-py3-none-macosx_15_0_arm64.whl; platform_system == "Darwin" and platform_release >= "24.0.0" and platform_release < "25.0.0"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.32.0/llama_cpp_binaries-0.32.0-py3-none-macosx_14_0_arm64.whl; platform_system == "Darwin" and platform_release >= "23.0.0" and platform_release < "24.0.0"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.32.0/llama_cpp_binaries-0.32.0-py3-none-macosx_13_0_arm64.whl; platform_system == "Darwin" and platform_release >= "22.0.0" and platform_release < "23.0.0"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.33.0/llama_cpp_binaries-0.33.0-py3-none-macosx_15_0_arm64.whl; platform_system == "Darwin" and platform_release >= "24.0.0" and platform_release < "25.0.0"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.33.0/llama_cpp_binaries-0.33.0-py3-none-macosx_14_0_arm64.whl; platform_system == "Darwin" and platform_release >= "23.0.0" and platform_release < "24.0.0"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.33.0/llama_cpp_binaries-0.33.0-py3-none-macosx_13_0_arm64.whl; platform_system == "Darwin" and platform_release >= "22.0.0" and platform_release < "23.0.0"

4
requirements/portable/requirements_cpu_only.txt
View file

@ -18,5 +18,5 @@ sse-starlette==1.6.5
tiktoken
# llama.cpp (CPU only, AVX2)
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.32.0/llama_cpp_binaries-0.32.0+cpuavx2-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.32.0/llama_cpp_binaries-0.32.0+cpuavx2-py3-none-win_amd64.whl; platform_system == "Windows"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.33.0/llama_cpp_binaries-0.33.0+cpuavx2-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.33.0/llama_cpp_binaries-0.33.0+cpuavx2-py3-none-win_amd64.whl; platform_system == "Windows"

4
requirements/portable/requirements_cpu_only_noavx2.txt
View file

@ -18,5 +18,5 @@ sse-starlette==1.6.5
tiktoken
# llama.cpp (CPU only, no AVX2)
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.32.0/llama_cpp_binaries-0.32.0+cpuavx-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.32.0/llama_cpp_binaries-0.32.0+cpuavx-py3-none-win_amd64.whl; platform_system == "Windows"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.33.0/llama_cpp_binaries-0.33.0+cpuavx-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.33.0/llama_cpp_binaries-0.33.0+cpuavx-py3-none-win_amd64.whl; platform_system == "Windows"

4
requirements/portable/requirements_noavx2.txt
View file

@ -18,5 +18,5 @@ sse-starlette==1.6.5
tiktoken
# CUDA wheels
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.32.0/llama_cpp_binaries-0.32.0+cu124avx-py3-none-win_amd64.whl; platform_system == "Windows"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.32.0/llama_cpp_binaries-0.32.0+cu124avx-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.33.0/llama_cpp_binaries-0.33.0+cu124avx-py3-none-win_amd64.whl; platform_system == "Windows"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.33.0/llama_cpp_binaries-0.33.0+cu124avx-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"

4
requirements/portable/requirements_vulkan.txt
View file

@ -18,5 +18,5 @@ sse-starlette==1.6.5
tiktoken
# CUDA wheels
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.32.0/llama_cpp_binaries-0.32.0+vulkan-py3-none-win_amd64.whl; platform_system == "Windows"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.32.0/llama_cpp_binaries-0.32.0+vulkan-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.33.0/llama_cpp_binaries-0.33.0+vulkan-py3-none-win_amd64.whl; platform_system == "Windows"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.33.0/llama_cpp_binaries-0.33.0+vulkan-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"

4
requirements/portable/requirements_vulkan_noavx2.txt
View file

@ -18,5 +18,5 @@ sse-starlette==1.6.5
tiktoken
# CUDA wheels
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.32.0/llama_cpp_binaries-0.32.0+vulkanavx-py3-none-win_amd64.whl; platform_system == "Windows"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.32.0/llama_cpp_binaries-0.32.0+vulkanavx-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.33.0/llama_cpp_binaries-0.33.0+vulkanavx-py3-none-win_amd64.whl; platform_system == "Windows"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.33.0/llama_cpp_binaries-0.33.0+vulkanavx-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"