diff --git a/Dockerfile b/Dockerfile index faa0a98a..21352603 100644 --- a/Dockerfile +++ b/Dockerfile @@ -1,10 +1,13 @@ FROM git.modelhub.org.cn:9443/enginex-iluvatar/bi100-3.2.3-x86-ubuntu20.04-py3.10-poc-llm-infer:v1.2.3 + +ENV PATH=/usr/local/corex/bin:/usr/local/corex-3.2.3/bin:/usr/local/openmpi/bin:${PATH} +ENV PYTHONPATH=/usr/local/corex/lib64/python3/dist-packages:/usr/local/corex/lib/python3/dist-packages +ENV LD_LIBRARY_PATH=/usr/local/corex/lib:/usr/local/corex/lib64:/usr/local/corex-3.2.3/lib:/usr/local/corex-3.2.3/lib64:/usr/local/openmpi/lib +ENV VLLM_ENGINE_ITERATION_TIMEOUT_S=3600 PYTHONUNBUFFERED=1 PYTHONFAULTHANDLER=1 BI100_EXECUTOR_STARTUP_DEBUG=1 ENABLE_CUSTOM_IPC=1 +ENV BI100_PREFIX_MODEL_FINGERPRINT=Qwen3.6-35B-A3B BI100_PREFIX_DTYPE=float16 BI100_PREFIX_TP_SIZE=4 + RUN mkdir -p /workspace WORKDIR /workspace/ -# Copy all our engine patches COPY ./qwen3_6_scripts /workspace/qwen3_6_scripts COPY ./computility-run.yaml /workspace/computility-run.yaml -# Make patch script executable and run it -RUN chmod +x /workspace/qwen3_6_scripts/patch_ops.sh && \ - bash /workspace/qwen3_6_scripts/patch_ops.sh 2>&1 | tee /workspace/patch_ops.log ; \ - echo "[Dockerfile] patch_ops exit code: $?" +RUN cd ./qwen3_6_scripts && bash ./patch_ops.sh diff --git a/computility-run.yaml b/computility-run.yaml index ac5b8ec2..41351f46 100644 --- a/computility-run.yaml +++ b/computility-run.yaml @@ -15,7 +15,7 @@ command: - -tp - '4' - --max-num-seqs - - '2' + - '1' - --disable-log-requests - --disable-frontend-multiprocessing - --max-num-batched-tokens diff --git a/qwen3_6_scripts/patch_ops.sh b/qwen3_6_scripts/patch_ops.sh index 3f70c7cf..87ec062d 100755 --- a/qwen3_6_scripts/patch_ops.sh +++ b/qwen3_6_scripts/patch_ops.sh @@ -28,7 +28,7 @@ # --max-seq-len-to-capture 32768 --enable-auto-tool-choice \ # --tool-call-parser qwen3_coder --reasoning-parser qwen3 -set -eo pipefail +set -euo pipefail # cd into this script's directory so ./relative paths work cd "$(dirname "${BASH_SOURCE[0]}")"