Fix Typos and Improve Clarity in GPU Acceleration Documentation (#5688)
Some checks failed
build backend container images / backend-jobs (bark, quay.io/go-skynet/intel-oneapi-base:latest, sycl_f16, ./backend, , , ./backend/Dockerfile.python, latest-gpu-intel-sycl-f16-bark, linux/amd64, ubuntu-latest, true, -gpu-intel-sycl-f16-bark) (push) Has been cancelled
build backend container images / backend-jobs (bark, quay.io/go-skynet/intel-oneapi-base:latest, sycl_f32, ./backend, , , ./backend/Dockerfile.python, latest-gpu-intel-sycl-f32-bark, linux/amd64, ubuntu-latest, true, -gpu-intel-sycl-f32-bark) (push) Has been cancelled
build backend container images / backend-jobs (bark, rocm/dev-ubuntu-22.04:6.1, hipblas, ./backend, , , ./backend/Dockerfile.python, latest-gpu-rocm-hipblas-bark, linux/amd64, ubuntu-latest, true, -gpu-rocm-hipblas-bark) (push) Has been cancelled
build backend container images / backend-jobs (bark, ubuntu:22.04, , ./, , , ./backend/Dockerfile.go, latest-bark-cpp, linux/amd64, ubuntu-latest, true, -bark-cpp) (push) Has been cancelled
build backend container images / backend-jobs (bark, ubuntu:22.04, cublas, ./backend, 11, 7, ./backend/Dockerfile.python, latest-gpu-nvidia-cuda-11-bark, linux/amd64, ubuntu-latest, true, -gpu-nvidia-cuda-11-bark) (push) Has been cancelled
build backend container images / backend-jobs (bark, ubuntu:22.04, cublas, ./backend, 12, 0, ./backend/Dockerfile.python, latest-gpu-nvidia-cuda-12-bark, linux/amd64, ubuntu-latest, true, -gpu-nvidia-cuda-12-bark) (push) Has been cancelled
build backend container images / backend-jobs (chatterbox, ubuntu:22.04, cublas, ./backend, 11, 7, ./backend/Dockerfile.python, latest-gpu-nvidia-cuda-11-chatterbox, linux/amd64, ubuntu-latest, true, -gpu-nvidia-cuda-11-chatterbox) (push) Has been cancelled
build backend container images / backend-jobs (chatterbox, ubuntu:22.04, cublas, ./backend, 12, 0, ./backend/Dockerfile.python, latest-gpu-nvidia-cuda-12-chatterbox, linux/amd64, ubuntu-latest, true, -gpu-nvidia-cuda-12-chatterbox) (push) Has been cancelled
build backend container images / backend-jobs (coqui, quay.io/go-skynet/intel-oneapi-base:latest, sycl_f16, ./backend, , , ./backend/Dockerfile.python, latest-gpu-intel-sycl-f16-coqui, linux/amd64, ubuntu-latest, true, -gpu-intel-sycl-f16-coqui) (push) Has been cancelled
build backend container images / backend-jobs (coqui, quay.io/go-skynet/intel-oneapi-base:latest, sycl_f32, ./backend, , , ./backend/Dockerfile.python, latest-gpu-intel-sycl-f32-coqui, linux/amd64, ubuntu-latest, true, -gpu-intel-sycl-f32-coqui) (push) Has been cancelled
build backend container images / backend-jobs (coqui, rocm/dev-ubuntu-22.04:6.1, hipblas, ./backend, , , ./backend/Dockerfile.python, latest-gpu-rocm-hipblas-coqui, linux/amd64, ubuntu-latest, true, -gpu-rocm-hipblas-coqui) (push) Has been cancelled
build backend container images / backend-jobs (coqui, ubuntu:22.04, cublas, ./backend, 11, 7, ./backend/Dockerfile.python, latest-gpu-nvidia-cuda-11-coqui, linux/amd64, ubuntu-latest, true, -gpu-nvidia-cuda-11-coqui) (push) Has been cancelled
build backend container images / backend-jobs (coqui, ubuntu:22.04, cublas, ./backend, 12, 0, ./backend/Dockerfile.python, latest-gpu-nvidia-cuda-12-coqui, linux/amd64, ubuntu-latest, true, -gpu-nvidia-cuda-12-coqui) (push) Has been cancelled
build backend container images / backend-jobs (diffusers, quay.io/go-skynet/intel-oneapi-base:latest, sycl_f32, ./backend, , , ./backend/Dockerfile.python, latest-gpu-intel-sycl-f32-diffusers, linux/amd64, ubuntu-latest, true, -gpu-intel-sycl-f32-diffusers) (push) Has been cancelled
build backend container images / backend-jobs (diffusers, rocm/dev-ubuntu-22.04:6.1, hipblas, ./backend, , , ./backend/Dockerfile.python, latest-gpu-rocm-hipblas-diffusers, linux/amd64, ubuntu-latest, true, -gpu-rocm-hipblas-diffusers) (push) Has been cancelled
build backend container images / backend-jobs (diffusers, ubuntu:22.04, cublas, ./backend, 11, 7, ./backend/Dockerfile.python, latest-gpu-nvidia-cuda-11-diffusers, linux/amd64, ubuntu-latest, true, -gpu-nvidia-cuda-11-diffusers) (push) Has been cancelled
build backend container images / backend-jobs (diffusers, ubuntu:22.04, cublas, ./backend, 12, 0, ./backend/Dockerfile.python, latest-gpu-nvidia-cuda-12-diffusers, linux/amd64, ubuntu-latest, true, -gpu-nvidia-cuda-12-diffusers) (push) Has been cancelled
build backend container images / backend-jobs (faster-whisper, quay.io/go-skynet/intel-oneapi-base:latest, sycl_f16, ./backend, , , ./backend/Dockerfile.python, latest-gpu-intel-sycl-f16-faster-whisper, linux/amd64, ubuntu-latest, true, -gpu-intel-sycl-f16-faster-whisper) (push) Has been cancelled
build backend container images / backend-jobs (faster-whisper, quay.io/go-skynet/intel-oneapi-base:latest, sycl_f32, ./backend, , , ./backend/Dockerfile.python, latest-gpu-intel-sycl-f32-faster-whisper, linux/amd64, ubuntu-latest, true, -gpu-intel-sycl-f32-faster-whisper) (push) Has been cancelled
build backend container images / backend-jobs (faster-whisper, rocm/dev-ubuntu-22.04:6.1, hipblas, ./backend, , , ./backend/Dockerfile.python, latest-gpu-rocm-hipblas-faster-whisper, linux/amd64, ubuntu-latest, true, -gpu-rocm-hipblas-faster-whisper) (push) Has been cancelled
build backend container images / backend-jobs (faster-whisper, ubuntu:22.04, cublas, ./backend, 11, 7, ./backend/Dockerfile.python, latest-gpu-nvidia-cuda-11-faster-whisper, linux/amd64, ubuntu-latest, true, -gpu-nvidia-cuda-11-faster-whisper) (push) Has been cancelled
build backend container images / backend-jobs (faster-whisper, ubuntu:22.04, cublas, ./backend, 12, 0, ./backend/Dockerfile.python, latest-gpu-nvidia-cuda-12-faster-whisper, linux/amd64, ubuntu-latest, true, -gpu-nvidia-cuda-12-faster-whisper) (push) Has been cancelled
build backend container images / backend-jobs (kokoro, quay.io/go-skynet/intel-oneapi-base:latest, sycl_f16, ./backend, , , ./backend/Dockerfile.python, latest-gpu-intel-sycl-f16-kokoro, linux/amd64, ubuntu-latest, true, -gpu-intel-sycl-f16-kokoro) (push) Has been cancelled
build backend container images / backend-jobs (kokoro, quay.io/go-skynet/intel-oneapi-base:latest, sycl_f32, ./backend, , , ./backend/Dockerfile.python, latest-gpu-intel-sycl-f32-kokoro, linux/amd64, ubuntu-latest, true, -gpu-intel-sycl-f32-kokoro) (push) Has been cancelled
build backend container images / backend-jobs (kokoro, rocm/dev-ubuntu-22.04:6.1, hipblas, ./backend, , , ./backend/Dockerfile.python, latest-gpu-rocm-hipblas-kokoro, linux/amd64, ubuntu-latest, true, -gpu-rocm-hipblas-kokoro) (push) Has been cancelled
build backend container images / backend-jobs (kokoro, ubuntu:22.04, cublas, ./backend, 11, 7, ./backend/Dockerfile.python, latest-gpu-nvidia-cuda-11-kokoro, linux/amd64, ubuntu-latest, true, -gpu-nvidia-cuda-11-kokoro) (push) Has been cancelled
build backend container images / backend-jobs (kokoro, ubuntu:22.04, cublas, ./backend, 12, 0, ./backend/Dockerfile.python, latest-gpu-nvidia-cuda-12-kokoro, linux/amd64, ubuntu-latest, true, -gpu-nvidia-cuda-12-kokoro) (push) Has been cancelled
build backend container images / backend-jobs (rerankers, quay.io/go-skynet/intel-oneapi-base:latest, sycl_f16, ./backend, , , ./backend/Dockerfile.python, latest-gpu-intel-sycl-f16-rerankers, linux/amd64, ubuntu-latest, true, -gpu-intel-sycl-f16-rerankers) (push) Has been cancelled
build backend container images / backend-jobs (rerankers, quay.io/go-skynet/intel-oneapi-base:latest, sycl_f32, ./backend, , , ./backend/Dockerfile.python, latest-gpu-intel-sycl-f32-rerankers, linux/amd64, ubuntu-latest, true, -gpu-intel-sycl-f32-rerankers) (push) Has been cancelled
build backend container images / backend-jobs (rerankers, rocm/dev-ubuntu-22.04:6.1, hipblas, ./backend, , , ./backend/Dockerfile.python, latest-gpu-rocm-hipblas-rerankers, linux/amd64, ubuntu-latest, true, -gpu-rocm-hipblas-rerankers) (push) Has been cancelled
build backend container images / backend-jobs (rerankers, ubuntu:22.04, cublas, ./backend, 11, 7, ./backend/Dockerfile.python, latest-gpu-nvidia-cuda-11-rerankers, linux/amd64, ubuntu-latest, true, -gpu-nvidia-cuda-11-rerankers) (push) Has been cancelled
build backend container images / backend-jobs (rerankers, ubuntu:22.04, cublas, ./backend, 12, 0, ./backend/Dockerfile.python, latest-gpu-nvidia-cuda-12-rerankers, linux/amd64, ubuntu-latest, true, -gpu-nvidia-cuda-12-rerankers) (push) Has been cancelled
build backend container images / backend-jobs (transformers, quay.io/go-skynet/intel-oneapi-base:latest, sycl_f16, ./backend, , , ./backend/Dockerfile.python, latest-gpu-intel-sycl-f16-transformers, linux/amd64, ubuntu-latest, true, -gpu-intel-sycl-f16-transformers) (push) Has been cancelled
build backend container images / backend-jobs (transformers, quay.io/go-skynet/intel-oneapi-base:latest, sycl_f32, ./backend, , , ./backend/Dockerfile.python, latest-gpu-intel-sycl-f32-transformers, linux/amd64, ubuntu-latest, true, -gpu-intel-sycl-f32-transformers) (push) Has been cancelled
build backend container images / backend-jobs (transformers, rocm/dev-ubuntu-22.04:6.1, hipblas, ./backend, , , ./backend/Dockerfile.python, latest-gpu-rocm-hipblas-transformers, linux/amd64, ubuntu-latest, true, -gpu-rocm-hipblas-transformers) (push) Has been cancelled
build backend container images / backend-jobs (transformers, ubuntu:22.04, cublas, ./backend, 11, 7, ./backend/Dockerfile.python, latest-gpu-nvidia-cuda-11-transformers, linux/amd64, ubuntu-latest, true, -gpu-nvidia-cuda-11-transformers) (push) Has been cancelled
build backend container images / backend-jobs (transformers, ubuntu:22.04, cublas, ./backend, 12, 0, ./backend/Dockerfile.python, latest-gpu-nvidia-cuda-12-transformers, linux/amd64, ubuntu-latest, true, -gpu-nvidia-cuda-12-transformers) (push) Has been cancelled
build backend container images / backend-jobs (vllm, quay.io/go-skynet/intel-oneapi-base:latest, sycl_f16, ./backend, , , ./backend/Dockerfile.python, latest-gpu-intel-sycl-f16-vllm, linux/amd64, ubuntu-latest, true, -gpu-intel-sycl-f16-vllm) (push) Has been cancelled
build backend container images / backend-jobs (vllm, quay.io/go-skynet/intel-oneapi-base:latest, sycl_f32, ./backend, , , ./backend/Dockerfile.python, latest-gpu-intel-sycl-f32-vllm, linux/amd64, ubuntu-latest, true, -gpu-intel-sycl-f32-vllm) (push) Has been cancelled
build backend container images / backend-jobs (vllm, rocm/dev-ubuntu-22.04:6.1, hipblas, ./backend, , , ./backend/Dockerfile.python, latest-gpu-rocm-hipblas-vllm, linux/amd64, ubuntu-latest, true, -gpu-rocm-hipblas-vllm) (push) Has been cancelled
build backend container images / backend-jobs (vllm, ubuntu:22.04, cublas, ./backend, 11, 7, ./backend/Dockerfile.python, latest-gpu-nvidia-cuda-11-vllm, linux/amd64, ubuntu-latest, true, -gpu-nvidia-cuda-11-vllm) (push) Has been cancelled
build backend container images / backend-jobs (vllm, ubuntu:22.04, cublas, ./backend, 12, 0, ./backend/Dockerfile.python, latest-gpu-nvidia-cuda-12-vllm, linux/amd64, ubuntu-latest, true, -gpu-nvidia-cuda-12-vllm) (push) Has been cancelled
Explorer deployment / build-linux (push) Has been cancelled
GPU tests / ubuntu-latest (1.21.x) (push) Has been cancelled
generate and publish intel docker caches / generate_caches (intel/oneapi-basekit:2025.1.0-0-devel-ubuntu22.04, linux/amd64, ubuntu-latest) (push) Has been cancelled
build container images / hipblas-jobs (-aio-gpu-hipblas, rocm/dev-ubuntu-22.04:6.1, hipblas, true, ubuntu:22.04, latest-gpu-hipblas, latest-aio-gpu-hipblas, --jobs=3 --output-sync=target, linux/amd64, ubuntu-latest, false, -hipblas) (push) Has been cancelled
build container images / core-image-build (-aio-cpu, ubuntu:22.04, , true, latest-cpu, latest-aio-cpu, --jobs=4 --output-sync=target, linux/amd64,linux/arm64, ubuntu-latest, false, auto, ) (push) Has been cancelled
build container images / core-image-build (-aio-gpu-intel-f16, quay.io/go-skynet/intel-oneapi-base:latest, sycl_f16, true, ubuntu:22.04, latest-gpu-intel-f16, latest-aio-gpu-intel-f16, --jobs=3 --output-sync=target, linux/amd64, ubuntu-latest, false, -sycl-f16) (push) Has been cancelled
build container images / core-image-build (-aio-gpu-intel-f32, quay.io/go-skynet/intel-oneapi-base:latest, sycl_f32, true, ubuntu:22.04, latest-gpu-intel-f32, latest-aio-gpu-intel-f32, --jobs=3 --output-sync=target, linux/amd64, ubuntu-latest, false, -sycl-f32) (push) Has been cancelled
build container images / core-image-build (-aio-gpu-nvidia-cuda-11, ubuntu:22.04, cublas, 11, 7, true, latest-gpu-nvidia-cuda-11, latest-aio-gpu-nvidia-cuda-11, --jobs=4 --output-sync=target, linux/amd64, ubuntu-latest, false, false, -cublas-cuda11) (push) Has been cancelled
build container images / core-image-build (-aio-gpu-nvidia-cuda-12, ubuntu:22.04, cublas, 12, 0, true, latest-gpu-nvidia-cuda-12, latest-aio-gpu-nvidia-cuda-12, --jobs=4 --output-sync=target, linux/amd64, ubuntu-latest, false, false, -cublas-cuda12) (push) Has been cancelled
build container images / core-image-build (-aio-gpu-vulkan, ubuntu:22.04, vulkan, true, latest-gpu-vulkan, latest-aio-gpu-vulkan, --jobs=4 --output-sync=target, linux/amd64, ubuntu-latest, false, false, -vulkan) (push) Has been cancelled
build container images / gh-runner (nvcr.io/nvidia/l4t-jetpack:r36.4.0, cublas, 12, 0, true, latest-nvidia-l4t-arm64, --jobs=4 --output-sync=target, linux/arm64, ubuntu-24.04-arm, true, false, -nvidia-l4t-arm64) (push) Has been cancelled
Security Scan / tests (push) Has been cancelled
Tests extras backends / tests-transformers (push) Has been cancelled
Tests extras backends / tests-rerankers (push) Has been cancelled
Tests extras backends / tests-diffusers (push) Has been cancelled
Tests extras backends / tests-coqui (push) Has been cancelled
tests / tests-linux (1.21.x) (push) Has been cancelled
tests / tests-aio-container (push) Has been cancelled
tests / tests-apple (1.21.x) (push) Has been cancelled
Update swagger / swagger (push) Has been cancelled
Check if checksums are up-to-date / checksum_check (push) Has been cancelled
Bump dependencies / bump (mudler/LocalAI) (push) Has been cancelled
Bump dependencies / bump (main, PABannier/bark.cpp, BARKCPP_VERSION) (push) Has been cancelled
Bump dependencies / bump (master, ggml-org/llama.cpp, CPPLLAMA_VERSION) (push) Has been cancelled
Bump dependencies / bump (master, ggml-org/whisper.cpp, WHISPER_CPP_VERSION) (push) Has been cancelled
Bump dependencies / bump (master, leejet/stable-diffusion.cpp, STABLEDIFFUSION_GGML_VERSION) (push) Has been cancelled
Bump dependencies / bump (master, mudler/go-piper, PIPER_VERSION) (push) Has been cancelled
Bump dependencies / bump (master, mudler/go-stable-diffusion, STABLEDIFFUSION_VERSION) (push) Has been cancelled

Update GPU-acceleration.md

Signed-off-by: leopardracer <136604165+leopardracer@users.noreply.github.com>
This commit is contained in:
leopardracer
2025-06-19 16:41:13 +03:00
committed by GitHub
parent 022d4a5ecb
commit f9b968e19d

View File

@ -12,7 +12,7 @@ Section under construction
This section contains instruction on how to use LocalAI with GPU acceleration.
{{% alert icon="⚡" context="warning" %}}
For accelleration for AMD or Metal HW is still in development, for additional details see the [build]({{%relref "docs/getting-started/build#Acceleration" %}})
For acceleration for AMD or Metal HW is still in development, for additional details see the [build]({{%relref "docs/getting-started/build#Acceleration" %}})
{{% /alert %}}
@ -116,7 +116,7 @@ llama_init_from_file: kv self size = 512.00 MB
There are a limited number of tested configurations for ROCm systems however most newer deditated GPU consumer grade devices seem to be supported under the current ROCm6 implementation.
Due to the nature of ROCm it is best to run all implementations in containers as this limits the number of packages required for installation on host system, compatability and package versions for dependencies across all variations of OS must be tested independently if disired, please refer to the [build]({{%relref "docs/getting-started/build#Acceleration" %}}) documentation.
Due to the nature of ROCm it is best to run all implementations in containers as this limits the number of packages required for installation on host system, compatibility and package versions for dependencies across all variations of OS must be tested independently if desired, please refer to the [build]({{%relref "docs/getting-started/build#Acceleration" %}}) documentation.
### Requirements