2026-06-01 20:20:48 -04:00
|
|
|
FROM vllm/vllm-openai:cu129-nightly
|
2026-06-01 19:28:08 -04:00
|
|
|
|
2026-06-01 20:20:48 -04:00
|
|
|
RUN sed -i 's/cute.arch.fmin/cutlass.min/g' /usr/local/lib/python3.12/dist-packages/vllm/models/deepseek_v4/nvidia/ops/sparse_attn_compress_cutedsl.py
|