Skip to content

Commit b6640fa

Browse files
gabe-l-hartgabe-l-hart
committed
Merge remote-tracking branch 'origin/master' into GraniteFour
* origin/master: (39 commits) server : vision support via libmtmd (ggml-org#12898) sycl : implementation of reordered Q4_0 MMVQ for Intel GPUs (ggml-org#12858) metal : optimize MoE for large batches (ggml-org#13388) CUDA: FA support for Deepseek (Ampere or newer) (ggml-org#13306) llama : do not crash if there is no CPU backend (ggml-org#13395) CUDA: fix crash on large batch size for MoE models (ggml-org#13384) imatrix : Add --parse-special for enabling parsing of special tokens in imatrix calculation (ggml-org#13389) llama-run: add support for downloading models from ModelScope (ggml-org#13370) mtmd : fix batch_view for m-rope (ggml-org#13397) llama : one-off chat template fix for Mistral-Small-2503 (ggml-org#13398) rpc : add rpc_msg_set_tensor_hash_req (ggml-org#13353) vulkan: Allow up to 4096 elements for mul_mat_id row_ids (ggml-org#13326) server : (webui) rename has_multimodal --> modalities (ggml-org#13393) ci : limit write permission to only the release step + fixes (ggml-org#13392) mtmd : Expose helper_decode_image_chunk (ggml-org#13366) server : (webui) fix a very small misalignment (ggml-org#13387) server : (webui) revamp the input area, plus many small UI improvements (ggml-org#13365) convert : support rope_scaling type and rope_type (ggml-org#13349) mtmd : fix the calculation of n_tokens for smolvlm (ggml-org#13381) context : allow cache-less context for embeddings (ggml-org#13108) ...
2 parents 1a87c58 + 33eff40 commit b6640fa

File tree

132 files changed

+6290
-4408
lines changed

Some content is hidden

Large Commits have some content hidden by default. Use the searchbox below for content that may be hidden.

132 files changed

+6290
-4408
lines changed

‎.github/actions/get-tag-name/action.yml

+22
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,22 @@
1+
name: "Determine tag name"
2+
description: "Determine the tag name to use for a release"
3+
outputs:
4+
name:
5+
description: "The name of the tag"
6+
value: ${{ steps.tag.outputs.name }}
7+
8+
runs:
9+
using: "composite"
10+
steps:
11+
- name: Determine tag name
12+
id: tag
13+
shell: bash
14+
run: |
15+
BUILD_NUMBER="$(git rev-list --count HEAD)"
16+
SHORT_HASH="$(git rev-parse --short=7 HEAD)"
17+
if [[ "${{ env.BRANCH_NAME }}" == "master" ]]; then
18+
echo "name=b${BUILD_NUMBER}" >> $GITHUB_OUTPUT
19+
else
20+
SAFE_NAME=$(echo "${{ env.BRANCH_NAME }}" | tr '/' '-')
21+
echo "name=${SAFE_NAME}-b${BUILD_NUMBER}-${SHORT_HASH}" >> $GITHUB_OUTPUT
22+
fi

‎.github/actions/windows-setup-cuda/action.yml

+67
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,67 @@
1+
name: "Windows - Setup CUDA Toolkit"
2+
description: "Setup CUDA Toolkit for Windows"
3+
inputs:
4+
cuda_version:
5+
description: "CUDA toolkit version"
6+
required: true
7+
8+
runs:
9+
using: "composite"
10+
steps:
11+
- name: Install Cuda Toolkit 11.7
12+
if: ${{ inputs.cuda_version == '11.7' }}
13+
shell: pwsh
14+
run: |
15+
mkdir -p "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7"
16+
choco install unzip -y
17+
curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_cudart/windows-x86_64/cuda_cudart-windows-x86_64-11.7.99-archive.zip"
18+
curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_nvcc/windows-x86_64/cuda_nvcc-windows-x86_64-11.7.99-archive.zip"
19+
curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_nvrtc/windows-x86_64/cuda_nvrtc-windows-x86_64-11.7.99-archive.zip"
20+
curl -O "https://developer.download.nvidia.com/compute/cuda/redist/libcublas/windows-x86_64/libcublas-windows-x86_64-11.7.4.6-archive.zip"
21+
curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_nvtx/windows-x86_64/cuda_nvtx-windows-x86_64-11.7.91-archive.zip"
22+
curl -O "https://developer.download.nvidia.com/compute/cuda/redist/visual_studio_integration/windows-x86_64/visual_studio_integration-windows-x86_64-11.7.91-archive.zip"
23+
curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_nvprof/windows-x86_64/cuda_nvprof-windows-x86_64-11.7.101-archive.zip"
24+
curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_cccl/windows-x86_64/cuda_cccl-windows-x86_64-11.7.91-archive.zip"
25+
unzip '*.zip' -d "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7"
26+
xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7\cuda_cudart-windows-x86_64-11.7.99-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7" /E /I /H /Y
27+
xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7\cuda_nvcc-windows-x86_64-11.7.99-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7" /E /I /H /Y
28+
xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7\cuda_nvrtc-windows-x86_64-11.7.99-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7" /E /I /H /Y
29+
xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7\libcublas-windows-x86_64-11.7.4.6-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7" /E /I /H /Y
30+
xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7\cuda_nvtx-windows-x86_64-11.7.91-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7" /E /I /H /Y
31+
xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7\visual_studio_integration-windows-x86_64-11.7.91-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7" /E /I /H /Y
32+
xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7\cuda_nvprof-windows-x86_64-11.7.101-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7" /E /I /H /Y
33+
xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7\cuda_cccl-windows-x86_64-11.7.91-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7" /E /I /H /Y
34+
echo "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7\bin" | Out-File -FilePath $env:GITHUB_PATH -Encoding utf8 -Append
35+
echo "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7\libnvvp" | Out-File -FilePath $env:GITHUB_PATH -Encoding utf8 -Append
36+
echo "CUDA_PATH=C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7" | Out-File -FilePath $env:GITHUB_ENV -Append -Encoding utf8
37+
echo "CUDA_PATH_V11_7=C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7" | Out-File -FilePath $env:GITHUB_ENV -Append -Encoding utf8
38+
39+
- name: Install Cuda Toolkit 12.4
40+
if: ${{ inputs.cuda_version == '12.4' }}
41+
shell: pwsh
42+
run: |
43+
mkdir -p "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4"
44+
choco install unzip -y
45+
curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_cudart/windows-x86_64/cuda_cudart-windows-x86_64-12.4.127-archive.zip"
46+
curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_nvcc/windows-x86_64/cuda_nvcc-windows-x86_64-12.4.131-archive.zip"
47+
curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_nvrtc/windows-x86_64/cuda_nvrtc-windows-x86_64-12.4.127-archive.zip"
48+
curl -O "https://developer.download.nvidia.com/compute/cuda/redist/libcublas/windows-x86_64/libcublas-windows-x86_64-12.4.5.8-archive.zip"
49+
curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_nvtx/windows-x86_64/cuda_nvtx-windows-x86_64-12.4.127-archive.zip"
50+
curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_profiler_api/windows-x86_64/cuda_profiler_api-windows-x86_64-12.4.127-archive.zip"
51+
curl -O "https://developer.download.nvidia.com/compute/cuda/redist/visual_studio_integration/windows-x86_64/visual_studio_integration-windows-x86_64-12.4.127-archive.zip"
52+
curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_nvprof/windows-x86_64/cuda_nvprof-windows-x86_64-12.4.127-archive.zip"
53+
curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_cccl/windows-x86_64/cuda_cccl-windows-x86_64-12.4.127-archive.zip"
54+
unzip '*.zip' -d "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4"
55+
xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\cuda_cudart-windows-x86_64-12.4.127-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" /E /I /H /Y
56+
xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\cuda_nvcc-windows-x86_64-12.4.131-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" /E /I /H /Y
57+
xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\cuda_nvrtc-windows-x86_64-12.4.127-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" /E /I /H /Y
58+
xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\libcublas-windows-x86_64-12.4.5.8-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" /E /I /H /Y
59+
xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\cuda_nvtx-windows-x86_64-12.4.127-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" /E /I /H /Y
60+
xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\cuda_profiler_api-windows-x86_64-12.4.127-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" /E /I /H /Y
61+
xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\visual_studio_integration-windows-x86_64-12.4.127-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" /E /I /H /Y
62+
xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\cuda_nvprof-windows-x86_64-12.4.127-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" /E /I /H /Y
63+
xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\cuda_cccl-windows-x86_64-12.4.127-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" /E /I /H /Y
64+
echo "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\bin" | Out-File -FilePath $env:GITHUB_PATH -Encoding utf8 -Append
65+
echo "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\libnvvp" | Out-File -FilePath $env:GITHUB_PATH -Encoding utf8 -Append
66+
echo "CUDA_PATH=C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" | Out-File -FilePath $env:GITHUB_ENV -Append -Encoding utf8
67+
echo "CUDA_PATH_V12_4=C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" | Out-File -FilePath $env:GITHUB_ENV -Append -Encoding utf8

0 commit comments

Comments
 (0)