From a96a3a2dacb54989e48adffa51530b1e0cc2fb05 Mon Sep 17 00:00:00 2001 From: eugr Date: Tue, 25 Nov 2025 12:48:58 -0800 Subject: [PATCH] Removed temporary patch for NVFP4 quants support as it's been merged into main --- Dockerfile | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/Dockerfile b/Dockerfile index 6ef5f3e..e6dd902 100644 --- a/Dockerfile +++ b/Dockerfile @@ -75,8 +75,8 @@ RUN python3 use_existing_torch.py && \ sed -i "/flashinfer/d" requirements/cuda.txt && \ pip install -r requirements/build.txt -# TEMPORARY - apply NVFP4 patch -RUN curl -L https://patch-diff.githubusercontent.com/raw/vllm-project/vllm/pull/29242.diff | git apply +# 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 # Final Build # Uses --no-build-isolation to respect the pre-installed Torch/FlashInfer