oobabooga/text-generation-webui
1
0
Fork 0
mirror of https://github.com/oobabooga/text-generation-webui.git synced 2025-12-06 07:12:10 +01:00
Code Issues Actions Packages Projects Releases Wiki Activity

Update llama.cpp

Browse source
This commit is contained in:
oobabooga 2025-10-20 19:43:26 -07:00
parent a156ebbf76
commit 9476123ee6
16 changed files with 35 additions and 35 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

4
requirements/full/requirements.txt
View file

@ -39,8 +39,8 @@ sse-starlette==1.6.5
tiktoken tiktoken
# CUDA wheels # CUDA wheels
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.53.0/llama_cpp_binaries-0.53.0+cu124-py3-none-win_amd64.whl; platform_system == "Windows" and python_version == "3.11" https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.54.0/llama_cpp_binaries-0.54.0+cu124-py3-none-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.53.0/llama_cpp_binaries-0.53.0+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/v0.54.0/llama_cpp_binaries-0.54.0+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/v0.0.10/exllamav3-0.0.10+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/v0.0.10/exllamav3-0.0.10+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/v0.0.10/exllamav3-0.0.10+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/exllamav3/releases/download/v0.0.10/exllamav3-0.0.10+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" 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_amd.txt
View file

@ -37,7 +37,7 @@ sse-starlette==1.6.5
tiktoken tiktoken
# AMD wheels # AMD wheels
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.53.0/llama_cpp_binaries-0.53.0+vulkan-py3-none-win_amd64.whl; platform_system == "Windows" https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.54.0/llama_cpp_binaries-0.54.0+vulkan-py3-none-win_amd64.whl; platform_system == "Windows"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.53.0/llama_cpp_binaries-0.53.0+vulkan-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.54.0/llama_cpp_binaries-0.54.0+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+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" 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

@ -37,7 +37,7 @@ sse-starlette==1.6.5
tiktoken tiktoken
# AMD wheels # AMD wheels
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.53.0/llama_cpp_binaries-0.53.0+vulkanavx-py3-none-win_amd64.whl; platform_system == "Windows" https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.54.0/llama_cpp_binaries-0.54.0+vulkanavx-py3-none-win_amd64.whl; platform_system == "Windows"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.53.0/llama_cpp_binaries-0.53.0+vulkanavx-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.54.0/llama_cpp_binaries-0.54.0+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+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" 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

@ -37,5 +37,5 @@ sse-starlette==1.6.5
tiktoken tiktoken
# Mac wheels # Mac wheels
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.53.0/llama_cpp_binaries-0.53.0-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/v0.54.0/llama_cpp_binaries-0.54.0-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/v0.53.0/llama_cpp_binaries-0.53.0-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/v0.54.0/llama_cpp_binaries-0.54.0-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"

6
requirements/full/requirements_apple_silicon.txt
View file

@ -37,6 +37,6 @@ sse-starlette==1.6.5
tiktoken tiktoken
# Mac wheels # Mac wheels
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.53.0/llama_cpp_binaries-0.53.0-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/v0.54.0/llama_cpp_binaries-0.54.0-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/v0.53.0/llama_cpp_binaries-0.53.0-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/v0.54.0/llama_cpp_binaries-0.54.0-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/v0.53.0/llama_cpp_binaries-0.53.0-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/v0.54.0/llama_cpp_binaries-0.54.0-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"

4
requirements/full/requirements_cpu_only.txt
View file

@ -37,5 +37,5 @@ sse-starlette==1.6.5
tiktoken tiktoken
# llama.cpp (CPU only, AVX2) # llama.cpp (CPU only, AVX2)
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.53.0/llama_cpp_binaries-0.53.0+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/v0.54.0/llama_cpp_binaries-0.54.0+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/v0.53.0/llama_cpp_binaries-0.53.0+cpuavx2-py3-none-win_amd64.whl; platform_system == "Windows" and python_version == "3.11" https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.54.0/llama_cpp_binaries-0.54.0+cpuavx2-py3-none-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"

4
requirements/full/requirements_cpu_only_noavx2.txt
View file

@ -37,5 +37,5 @@ sse-starlette==1.6.5
tiktoken tiktoken
# llama.cpp (CPU only, no AVX2) # llama.cpp (CPU only, no AVX2)
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.53.0/llama_cpp_binaries-0.53.0+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/v0.54.0/llama_cpp_binaries-0.54.0+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/v0.53.0/llama_cpp_binaries-0.53.0+cpuavx-py3-none-win_amd64.whl; platform_system == "Windows" and python_version == "3.11" https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.54.0/llama_cpp_binaries-0.54.0+cpuavx-py3-none-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"

4
requirements/full/requirements_noavx2.txt
View file

@ -39,8 +39,8 @@ sse-starlette==1.6.5
tiktoken tiktoken
# CUDA wheels # CUDA wheels
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.53.0/llama_cpp_binaries-0.53.0+cu124avx-py3-none-win_amd64.whl; platform_system == "Windows" and python_version == "3.11" https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.54.0/llama_cpp_binaries-0.54.0+cu124avx-py3-none-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.53.0/llama_cpp_binaries-0.53.0+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/v0.54.0/llama_cpp_binaries-0.54.0+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/v0.0.10/exllamav3-0.0.10+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/v0.0.10/exllamav3-0.0.10+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/v0.0.10/exllamav3-0.0.10+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/exllamav3/releases/download/v0.0.10/exllamav3-0.0.10+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" 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/portable/requirements.txt
View file

@ -22,5 +22,5 @@ sse-starlette==1.6.5
tiktoken tiktoken
# CUDA wheels # CUDA wheels
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.53.0/llama_cpp_binaries-0.53.0+cu124-py3-none-win_amd64.whl; platform_system == "Windows" https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.54.0/llama_cpp_binaries-0.54.0+cu124-py3-none-win_amd64.whl; platform_system == "Windows"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.53.0/llama_cpp_binaries-0.53.0+cu124-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.54.0/llama_cpp_binaries-0.54.0+cu124-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"

6
requirements/portable/requirements_apple_intel.txt
View file

@ -22,6 +22,6 @@ sse-starlette==1.6.5
tiktoken tiktoken
# Mac wheels # Mac wheels
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.53.0/llama_cpp_binaries-0.53.0-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/v0.54.0/llama_cpp_binaries-0.54.0-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/v0.53.0/llama_cpp_binaries-0.53.0-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/v0.54.0/llama_cpp_binaries-0.54.0-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/v0.53.0/llama_cpp_binaries-0.53.0-py3-none-macosx_13_0_x86_64.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/v0.54.0/llama_cpp_binaries-0.54.0-py3-none-macosx_13_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "22.0.0" and platform_release < "23.0.0"

6
requirements/portable/requirements_apple_silicon.txt
View file

@ -22,6 +22,6 @@ sse-starlette==1.6.5
tiktoken tiktoken
# Mac wheels # Mac wheels
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.53.0/llama_cpp_binaries-0.53.0-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/v0.54.0/llama_cpp_binaries-0.54.0-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/v0.53.0/llama_cpp_binaries-0.53.0-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/v0.54.0/llama_cpp_binaries-0.54.0-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/v0.53.0/llama_cpp_binaries-0.53.0-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/v0.54.0/llama_cpp_binaries-0.54.0-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

@ -22,5 +22,5 @@ sse-starlette==1.6.5
tiktoken tiktoken
# llama.cpp (CPU only, AVX2) # llama.cpp (CPU only, AVX2)
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.53.0/llama_cpp_binaries-0.53.0+cpuavx2-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.54.0/llama_cpp_binaries-0.54.0+cpuavx2-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.53.0/llama_cpp_binaries-0.53.0+cpuavx2-py3-none-win_amd64.whl; platform_system == "Windows" https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.54.0/llama_cpp_binaries-0.54.0+cpuavx2-py3-none-win_amd64.whl; platform_system == "Windows"

4
requirements/portable/requirements_cpu_only_noavx2.txt
View file

@ -22,5 +22,5 @@ sse-starlette==1.6.5
tiktoken tiktoken
# llama.cpp (CPU only, no AVX2) # llama.cpp (CPU only, no AVX2)
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.53.0/llama_cpp_binaries-0.53.0+cpuavx-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.54.0/llama_cpp_binaries-0.54.0+cpuavx-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.53.0/llama_cpp_binaries-0.53.0+cpuavx-py3-none-win_amd64.whl; platform_system == "Windows" https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.54.0/llama_cpp_binaries-0.54.0+cpuavx-py3-none-win_amd64.whl; platform_system == "Windows"

4
requirements/portable/requirements_noavx2.txt
View file

@ -22,5 +22,5 @@ sse-starlette==1.6.5
tiktoken tiktoken
# CUDA wheels # CUDA wheels
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.53.0/llama_cpp_binaries-0.53.0+cu124avx-py3-none-win_amd64.whl; platform_system == "Windows" https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.54.0/llama_cpp_binaries-0.54.0+cu124avx-py3-none-win_amd64.whl; platform_system == "Windows"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.53.0/llama_cpp_binaries-0.53.0+cu124avx-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.54.0/llama_cpp_binaries-0.54.0+cu124avx-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"

4
requirements/portable/requirements_vulkan.txt
View file

@ -22,5 +22,5 @@ sse-starlette==1.6.5
tiktoken tiktoken
# CUDA wheels # CUDA wheels
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.53.0/llama_cpp_binaries-0.53.0+vulkan-py3-none-win_amd64.whl; platform_system == "Windows" https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.54.0/llama_cpp_binaries-0.54.0+vulkan-py3-none-win_amd64.whl; platform_system == "Windows"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.53.0/llama_cpp_binaries-0.53.0+vulkan-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.54.0/llama_cpp_binaries-0.54.0+vulkan-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"

4
requirements/portable/requirements_vulkan_noavx2.txt
View file

@ -22,5 +22,5 @@ sse-starlette==1.6.5
tiktoken tiktoken
# CUDA wheels # CUDA wheels
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.53.0/llama_cpp_binaries-0.53.0+vulkanavx-py3-none-win_amd64.whl; platform_system == "Windows" https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.54.0/llama_cpp_binaries-0.54.0+vulkanavx-py3-none-win_amd64.whl; platform_system == "Windows"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.53.0/llama_cpp_binaries-0.53.0+vulkanavx-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.54.0/llama_cpp_binaries-0.54.0+vulkanavx-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"