diff --git a/experiments/pro6000/kimi3_pro6000_sglang_tp32ep32_moe_backend_prefill/Dockerfile b/experiments/pro6000/kimi3_pro6000_sglang_tp32ep32_moe_backend_prefill/Dockerfile index 17fbeb2..b394e24 100644 --- a/experiments/pro6000/kimi3_pro6000_sglang_tp32ep32_moe_backend_prefill/Dockerfile +++ b/experiments/pro6000/kimi3_pro6000_sglang_tp32ep32_moe_backend_prefill/Dockerfile @@ -9,9 +9,10 @@ RUN rm -rf \ /usr/local/lib/python3.12/dist-packages/flashinfer \ /usr/local/lib/python3.12/dist-packages/flashinfer_python-*.dist-info -COPY flashinfer_python-0.6.18-py3-none-any.whl /tmp/flashinfer_python.whl -RUN python3 -m pip install --no-deps --force-reinstall /tmp/flashinfer_python.whl && \ - rm -f /tmp/flashinfer_python.whl +COPY flashinfer_python-0.6.18-py3-none-any.whl /tmp/flashinfer_python-0.6.18-py3-none-any.whl +RUN python3 -m pip install --no-deps --force-reinstall \ + /tmp/flashinfer_python-0.6.18-py3-none-any.whl && \ + rm -f /tmp/flashinfer_python-0.6.18-py3-none-any.whl # The wheel contains Python/C++ sources. These three libraries are the exact # SM120 AOT artifacts that passed the Phase 3/4 correctness gate. @@ -31,4 +32,3 @@ RUN python3 -c "from pathlib import Path; p=Path('/sgl-workspace/sglang/python/s LABEL ai.meta-stone.purpose="Kimi-K3 SM120 FlashInfer MXFP4 Phase 5 acceptance" \ ai.meta-stone.sglang.patch="fb929bb" \ ai.meta-stone.flashinfer.patch="7d1a4ee" -