Update llama.cpp

This commit is contained in:
oobabooga
2026-05-31 22:22:00 -07:00
parent fbaa8a3d90
commit ed888c71f2
15 changed files with 31 additions and 31 deletions

View File

@@ -44,10 +44,10 @@ sse-starlette==1.6.5
tiktoken tiktoken
# CUDA wheels # CUDA wheels
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.136.0/llama_cpp_binaries-0.136.0+cu124-py3-none-win_amd64.whl; platform_system == "Windows" https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.138.0/llama_cpp_binaries-0.138.0+cu124-py3-none-win_amd64.whl; platform_system == "Windows"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.136.0/llama_cpp_binaries-0.136.0+cu124-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.138.0/llama_cpp_binaries-0.138.0+cu124-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.136.0/ik_llama_cpp_binaries-0.136.0+cu124-py3-none-win_amd64.whl; platform_system == "Windows" https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.138.0/ik_llama_cpp_binaries-0.138.0+cu124-py3-none-win_amd64.whl; platform_system == "Windows"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.136.0/ik_llama_cpp_binaries-0.136.0+cu124-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.138.0/ik_llama_cpp_binaries-0.138.0+cu124-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
https://github.com/turboderp-org/exllamav3/releases/download/v0.0.34/exllamav3-0.0.34+cu128.torch2.9.0-cp313-cp313-win_amd64.whl; platform_system == "Windows" and python_version == "3.13" https://github.com/turboderp-org/exllamav3/releases/download/v0.0.34/exllamav3-0.0.34+cu128.torch2.9.0-cp313-cp313-win_amd64.whl; platform_system == "Windows" and python_version == "3.13"
https://github.com/turboderp-org/exllamav3/releases/download/v0.0.34/exllamav3-0.0.34+cu128.torch2.9.0-cp313-cp313-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.13" https://github.com/turboderp-org/exllamav3/releases/download/v0.0.34/exllamav3-0.0.34+cu128.torch2.9.0-cp313-cp313-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.13"
https://github.com/mjun0812/flash-attention-prebuild-wheels/releases/download/v0.7.13/flash_attn-2.8.3+cu128torch2.9-cp313-cp313-win_amd64.whl; platform_system == "Windows" and python_version == "3.13" https://github.com/mjun0812/flash-attention-prebuild-wheels/releases/download/v0.7.13/flash_attn-2.8.3+cu128torch2.9-cp313-cp313-win_amd64.whl; platform_system == "Windows" and python_version == "3.13"

View File

@@ -39,5 +39,5 @@ sse-starlette==1.6.5
tiktoken tiktoken
# AMD wheels # AMD wheels
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.136.0/llama_cpp_binaries-0.136.0+rocm7.2-py3-none-win_amd64.whl; platform_system == "Windows" https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.138.0/llama_cpp_binaries-0.138.0+rocm7.2-py3-none-win_amd64.whl; platform_system == "Windows"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.136.0/llama_cpp_binaries-0.136.0+rocm7.2-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.138.0/llama_cpp_binaries-0.138.0+rocm7.2-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"

View File

@@ -39,4 +39,4 @@ sse-starlette==1.6.5
tiktoken tiktoken
# Mac wheels # Mac wheels
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.136.0/llama_cpp_binaries-0.136.0-py3-none-macosx_13_0_x86_64.whl; platform_system == "Darwin" https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.138.0/llama_cpp_binaries-0.138.0-py3-none-macosx_13_0_x86_64.whl; platform_system == "Darwin"

View File

@@ -39,4 +39,4 @@ sse-starlette==1.6.5
tiktoken tiktoken
# Mac wheels # Mac wheels
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.136.0/llama_cpp_binaries-0.136.0-py3-none-macosx_13_0_arm64.whl; platform_system == "Darwin" https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.138.0/llama_cpp_binaries-0.138.0-py3-none-macosx_13_0_arm64.whl; platform_system == "Darwin"

View File

@@ -39,7 +39,7 @@ sse-starlette==1.6.5
tiktoken tiktoken
# llama.cpp (CPU only) # llama.cpp (CPU only)
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.136.0/llama_cpp_binaries-0.136.0+cpu-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.138.0/llama_cpp_binaries-0.138.0+cpu-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.136.0/llama_cpp_binaries-0.136.0+cpu-py3-none-win_amd64.whl; platform_system == "Windows" https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.138.0/llama_cpp_binaries-0.138.0+cpu-py3-none-win_amd64.whl; platform_system == "Windows"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.136.0/ik_llama_cpp_binaries-0.136.0+cpu-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.138.0/ik_llama_cpp_binaries-0.138.0+cpu-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.136.0/ik_llama_cpp_binaries-0.136.0+cpu-py3-none-win_amd64.whl; platform_system == "Windows" https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.138.0/ik_llama_cpp_binaries-0.138.0+cpu-py3-none-win_amd64.whl; platform_system == "Windows"

View File

@@ -25,5 +25,5 @@ sse-starlette==1.6.5
tiktoken tiktoken
# CUDA wheels # CUDA wheels
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.136.0/llama_cpp_binaries-0.136.0+cu124-py3-none-win_amd64.whl; platform_system == "Windows" https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.138.0/llama_cpp_binaries-0.138.0+cu124-py3-none-win_amd64.whl; platform_system == "Windows"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.136.0/llama_cpp_binaries-0.136.0+cu124-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.138.0/llama_cpp_binaries-0.138.0+cu124-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"

View File

@@ -25,5 +25,5 @@ sse-starlette==1.6.5
tiktoken tiktoken
# AMD wheels # AMD wheels
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.136.0/llama_cpp_binaries-0.136.0+rocm7.2-py3-none-win_amd64.whl; platform_system == "Windows" https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.138.0/llama_cpp_binaries-0.138.0+rocm7.2-py3-none-win_amd64.whl; platform_system == "Windows"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.136.0/llama_cpp_binaries-0.136.0+rocm7.2-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.138.0/llama_cpp_binaries-0.138.0+rocm7.2-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"

View File

@@ -25,4 +25,4 @@ sse-starlette==1.6.5
tiktoken tiktoken
# Mac wheels # Mac wheels
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.136.0/llama_cpp_binaries-0.136.0-py3-none-macosx_13_0_x86_64.whl; platform_system == "Darwin" https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.138.0/llama_cpp_binaries-0.138.0-py3-none-macosx_13_0_x86_64.whl; platform_system == "Darwin"

View File

@@ -25,4 +25,4 @@ sse-starlette==1.6.5
tiktoken tiktoken
# Mac wheels # Mac wheels
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.136.0/llama_cpp_binaries-0.136.0-py3-none-macosx_13_0_arm64.whl; platform_system == "Darwin" https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.138.0/llama_cpp_binaries-0.138.0-py3-none-macosx_13_0_arm64.whl; platform_system == "Darwin"

View File

@@ -25,5 +25,5 @@ sse-starlette==1.6.5
tiktoken tiktoken
# llama.cpp (CPU only) # llama.cpp (CPU only)
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.136.0/llama_cpp_binaries-0.136.0+cpu-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.138.0/llama_cpp_binaries-0.138.0+cpu-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.136.0/llama_cpp_binaries-0.136.0+cpu-py3-none-win_amd64.whl; platform_system == "Windows" https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.138.0/llama_cpp_binaries-0.138.0+cpu-py3-none-win_amd64.whl; platform_system == "Windows"

View File

@@ -25,6 +25,6 @@ sse-starlette==1.6.5
tiktoken tiktoken
# CUDA wheels # CUDA wheels
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.136.0/llama_cpp_binaries-0.136.0+cu131-py3-none-win_amd64.whl; platform_system == "Windows" https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.138.0/llama_cpp_binaries-0.138.0+cu131-py3-none-win_amd64.whl; platform_system == "Windows"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.136.0/llama_cpp_binaries-0.136.0+cu131-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.138.0/llama_cpp_binaries-0.138.0+cu131-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.136.0/llama_cpp_binaries-0.136.0+cu131-py3-none-linux_aarch64.whl; platform_system == "Linux" and platform_machine == "aarch64" https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.138.0/llama_cpp_binaries-0.138.0+cu131-py3-none-linux_aarch64.whl; platform_system == "Linux" and platform_machine == "aarch64"

View File

@@ -25,5 +25,5 @@ sse-starlette==1.6.5
tiktoken tiktoken
# CUDA wheels # CUDA wheels
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.136.0/ik_llama_cpp_binaries-0.136.0+cu124-py3-none-win_amd64.whl; platform_system == "Windows" https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.138.0/ik_llama_cpp_binaries-0.138.0+cu124-py3-none-win_amd64.whl; platform_system == "Windows"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.136.0/ik_llama_cpp_binaries-0.136.0+cu124-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.138.0/ik_llama_cpp_binaries-0.138.0+cu124-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"

View File

@@ -25,5 +25,5 @@ sse-starlette==1.6.5
tiktoken tiktoken
# ik_llama.cpp (CPU only) # ik_llama.cpp (CPU only)
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.136.0/ik_llama_cpp_binaries-0.136.0+cpu-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.138.0/ik_llama_cpp_binaries-0.138.0+cpu-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.136.0/ik_llama_cpp_binaries-0.136.0+cpu-py3-none-win_amd64.whl; platform_system == "Windows" https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.138.0/ik_llama_cpp_binaries-0.138.0+cpu-py3-none-win_amd64.whl; platform_system == "Windows"

View File

@@ -25,5 +25,5 @@ sse-starlette==1.6.5
tiktoken tiktoken
# CUDA wheels # CUDA wheels
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.136.0/ik_llama_cpp_binaries-0.136.0+cu131-py3-none-win_amd64.whl; platform_system == "Windows" https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.138.0/ik_llama_cpp_binaries-0.138.0+cu131-py3-none-win_amd64.whl; platform_system == "Windows"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.136.0/ik_llama_cpp_binaries-0.136.0+cu131-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.138.0/ik_llama_cpp_binaries-0.138.0+cu131-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"

View File

@@ -25,5 +25,5 @@ sse-starlette==1.6.5
tiktoken tiktoken
# Vulkan wheels # Vulkan wheels
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.136.0/llama_cpp_binaries-0.136.0+vulkan-py3-none-win_amd64.whl; platform_system == "Windows" https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.138.0/llama_cpp_binaries-0.138.0+vulkan-py3-none-win_amd64.whl; platform_system == "Windows"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.136.0/llama_cpp_binaries-0.136.0+vulkan-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.138.0/llama_cpp_binaries-0.138.0+vulkan-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"