#!/bin/bash
set -euo pipefail
docker run -d --name retest-v620-fp16-tp2-mtp2-v620-fp16-tp2-mtp2-r1-2e69b6f871 --network host --ipc host --cpuset-cpus 0-7,16-23 --cpuset-mems 0 --security-opt label=disable --shm-size 67108864 --device /dev/kfd:/dev/kfd:rwm --device /dev/dri/card5:/dev/dri/card5:rwm --device /dev/dri/card6:/dev/dri/card6:rwm --device /dev/dri/renderD133:/dev/dri/renderD133:rwm --device /dev/dri/renderD134:/dev/dri/renderD134:rwm --user root --workdir /tmp -e VLLM_DISABLE_COMPILE_CACHE=1 -e PATH=/opt/venv/bin:/opt/venv/lib/python3.12/site-packages/_rocm_sdk_devel/bin:/opt/venv/lib/python3.12/site-packages/_rocm_sdk_devel/lib/llvm/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin -e ROCM_HOME=/opt/venv/lib/python3.12/site-packages/_rocm_sdk_devel -e ROCM_PATH=/opt/venv/lib/python3.12/site-packages/_rocm_sdk_devel -e HIP_HOME=/opt/venv/lib/python3.12/site-packages/_rocm_sdk_devel -e LD_LIBRARY_PATH=/opt/venv/lib/python3.12/site-packages/_rocm_sdk_devel/lib:/opt/venv/lib/python3.12/site-packages/_rocm_sdk_libraries/lib:/opt/venv/lib/python3.12/site-packages/torch/lib:/usr/local/lib -e ROCM_VERSION=7.14.0 -e TORCH_VERSION=2.12.0+rocm7.14.0 -e VLLM_TARGET_DEVICE=rocm -e VLLM_VERSION_OVERRIDE=0.0.0+gfx1030 -e PYTORCH_ROCM_ARCH=gfx1030 -e GPU_ARCHS=gfx1030 -e AMDGPU_TARGETS=gfx1030 -e CMAKE_HIP_ARCHITECTURES=gfx1030 -e PYTHONDONTWRITEBYTECODE=1 -e PIP_NO_CACHE_DIR=1 -e PIP_DISABLE_PIP_VERSION_CHECK=1 --mount type=bind,src=/home/ai/qwen38-release-retests-20261026/v620-fp16-tp2-mtp2-r1/cache/.triton,dst=/root/.triton --mount type=bind,src=/home/ai/qwen38-release-retests-20261026/v620-fp16-tp2-mtp2-r1/cache/torchinductor,dst=/tmp/torchinductor_root --mount type=bind,src=/usr/share/ollama/localaiservers-vnext/models/Qwen3.8-27B-1d4bf0f2ff6012fd82039f2fa52739d0dd7c60c0,dst=/opt/local-models/qwen38-27b-hf,readonly --mount type=bind,src=/home/ai/qwen38-release-retests-20261026/v620-fp16-tp2-mtp2-r1/cache/vllm,dst=/root/.cache/vllm --mount type=bind,src=/home/ai/qwen38-release-retests-20261026/v620-fp16-tp2-mtp2-r1/cache/torch_extensions,dst=/root/.cache/torch_extensions --entrypoint /usr/bin/env sha256:a98060dd75e701abc267843ccd7d8513c7baf7b6abb168c6c289bd2dbad5d399 V756F94_BOUNDARY_MODE=posted DO_NOT_TRACK=1 GPU_DEVICE_ORDINAL=0,1 GPU_MAX_HW_QUEUES=1 HSA_OVERRIDE_GFX_VERSION=10.3.0 OMP_NUM_THREADS=4 TEMP=/tmp/torchinductor_root TMPDIR=/tmp/torchinductor_root TMP=/tmp/torchinductor_root TORCH_BLAS_PREFER_HIPBLASLT=0 TRITON_CACHE_DIR=/root/.triton VLLM_EXECUTE_MODEL_TIMEOUT_SECONDS=1800 VLLM_GPU_MEMORY_UTILIZATION=0.95 VLLM_LOGGING_LEVEL=INFO VLLM_PORT=9002 VLLM_RDNA_FORCE_FP16=1 VLLM_WORKER_MULTIPROC_METHOD=spawn NCCL_P2P_DISABLE=0 NCCL_ALGO=Tree NCCL_PROTO=LL NCCL_MIN_NCHANNELS=4 NCCL_MAX_NCHANNELS=4 NCCL_NTHREADS=256 TORCHINDUCTOR_CACHE_DIR=/tmp/torchinductor_root HIP_VISIBLE_DEVICES=0,1 CUDA_VISIBLE_DEVICES=0,1 ROCR_VISIBLE_DEVICES=0,1 VLLM_CACHE_ROOT=/root/.cache/vllm PYTORCH_ROCM_ARCH=gfx1030 PYTHONHASHSEED=0 /opt/venv/bin/vllm serve /opt/local-models/qwen38-27b-hf --served-model-name Qwen/Qwen3.8-27B --enable-auto-tool-choice --tool-call-parser qwen3_coder --dtype half --host 0.0.0.0 --port 9002 --tensor-parallel-size 2 --max-model-len 131072 --gpu-memory-utilization 0.95 --trust-remote-code --generation-config vllm -O=3 --reasoning-parser qwen3 --async-scheduling --hf-overrides '{"architectures":["Qwen3_5ForCausalLM"]}' --language-model-only --max-num-seqs 2 --max-num-batched-tokens 2048 --mamba-ssm-cache-dtype float32 --no-enable-prefix-caching --no-enforce-eager --attention-backend TRITON_ATTN --disable-custom-all-reduce --seed 0 --worker-cls vllm.vnext_qwen38_worker.Worker --speculative-config '{"method":"mtp","num_speculative_tokens":2}'
