software-engineering/spark-vllm-docker
2
0
Fork 0
Code Issues Actions Packages Projects Releases Wiki Activity

Removed temporary patch for NVFP4 quants support as it's been merged into main

Browse Source
This commit is contained in:
eugr
2025-11-25 12:48:58 -08:00
parent a93bd56389
commit a96a3a2dac
1 changed files with 2 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
Dockerfile
View File

@@ -75,8 +75,8 @@ RUN python3 use_existing_torch.py && \
sed -i "/flashinfer/d" requirements/cuda.txt && \ sed -i "/flashinfer/d" requirements/cuda.txt && \
pip install -r requirements/build.txt pip install -r requirements/build.txt
# TEMPORARY - apply NVFP4 patch # TEMPORARY - apply NVFP4 patch - MERGED ON 11/25/2025 - TODO: test and remove from Dockerfile
RUN curl -L https://patch-diff.githubusercontent.com/raw/vllm-project/vllm/pull/29242.diff | git apply # RUN curl -L https://patch-diff.githubusercontent.com/raw/vllm-project/vllm/pull/29242.diff | git apply
# Final Build # Final Build
# Uses --no-build-isolation to respect the pre-installed Torch/FlashInfer # Uses --no-build-isolation to respect the pre-installed Torch/FlashInfer