#!/bin/bash
set -euo pipefail
docker run -d --name retest-mi50-fp16-tp4-mtp0-mi50-fp16-tp4-mtp0-r2 --network host --ipc host --cpuset-cpus 0-7,16-23 --security-opt label=disable --shm-size 67108864 --device /dev/kfd:/dev/kfd:rwm --device /dev/dri/renderD129:/dev/dri/renderD129:rwm --device /dev/dri/renderD130:/dev/dri/renderD130:rwm --device /dev/dri/renderD131:/dev/dri/renderD131:rwm --device /dev/dri/renderD132:/dev/dri/renderD132:rwm --user root --workdir /tmp -e VLLM_GFX906_PACKED_QKVZ_CONV=1 -e HIP_VISIBLE_DEVICES=0,1,2,3 -e VLLM_GFX906_ROWPAR_MUTABLE_AR=0 -e TRANSFORMERS_OFFLINE=1 -e VLLM_EXECUTE_MODEL_TIMEOUT_SECONDS=1800 -e VLLM_GFX906_QWEN_OUTPUT_FIXED3=1 -e VLLM_GFX906_QWEN_QKV_FIXED3=1 -e GFX906_MODEL_IDENTITY_DIR=/runwork -e VLLM_GFX906_QWEN_MLP_FIXED3_STRICT=1 -e VLLM_GFX906_QWEN_GDN_FIXED3=1 -e VLLM_ENABLE_FLA_PACKED_RECURRENT_DECODE=1 -e VLLM_GFX906_PERSISTENT_AR=0 -e VLLM_GFX906_PERSISTENT_AR_KIND_ROUTE=0 -e VLLM_GFX906_QWEN_MLP_FIXED3=1 -e VLLM_GFX906_PERSISTENT_AR_PREINIT_ON_GRAPH_CAPTURE=0 -e HF_HUB_OFFLINE=1 -e VLLM_GFX906_QWEN_MLP_FIXED3_EXT_PATH=/opt/vllm_patch_bundle/native/fixed3/v756f96_fixed3_core.so -e VLLM_GFX906_ROWPAR_BOUNDARY_CUT=0 -e PATH=/opt/venv/bin:/opt/rocm/bin:/opt/rocm/llvm/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin -e ROCM_VERSION=7.2.1 -e AMDGPU_VERSION=not-installed -e PYTORCH_INDEX_URL=https://download.pytorch.org/whl/rocm7.2 -e TORCH_VERSION=2.11.0+rocm7.2 -e TORCHVISION_VERSION=0.26.0+rocm7.2 -e TORCHAUDIO_VERSION=2.11.0+rocm7.2 -e PYTORCH_TRITON_ROCM_VERSION=3.6.0 -e AMDSMI_VERSION=7.0.2 -e ROCM72_EXPERIMENT_SKIP_DPKG_LOCKS=1 -e VLLM_COMMIT=6a52668c14dc9cb94a270d94bfec735fe627ed0c -e VLLM_PACKAGE_VERSION=0.0.0+gfx906 -e VLLM_VERSION_OVERRIDE=0.0.0+gfx906 -e SOURCE_DATE_EPOCH=1764000000 -e VLLM_TARGET_DEVICE=rocm -e PYTORCH_ROCM_ARCH=gfx906 -e GPU_ARCHS=gfx906 -e AMDGPU_TARGETS=gfx906 -e CMAKE_HIP_ARCHITECTURES=gfx906 -e FLASH_ATTENTION_TRITON_AMD_ENABLE=TRUE -e FLASH_ATTENTION_TRITON_AMD_REF=TRUE -e LD_LIBRARY_PATH=/opt/gfx906:/rccl-overlay/install/lib:/opt/rocm/lib:/opt/rocm/lib64:/usr/local/lib: -e PYTHONPATH=/opt/qwen36-python -e PYTHONUNBUFFERED=1 -e PYTHONHASHSEED=0 -e PIP_NO_CACHE_DIR=1 -e PIP_NO_COMPILE=1 -e PIP_DISABLE_PIP_VERSION_CHECK=1 -e PYTHONDONTWRITEBYTECODE=1 -e LANG=C.UTF-8 -e LC_ALL=C.UTF-8 -e TZ=Etc/UTC -e VLLM_PATCH_BUNDLE=/opt/vllm_patch_bundle -e V756F105_CUSTOM_AR_LIBRARY=/opt/localaiservers/v756f105r3/lib/v756f105r3_custom_ar.so -e VLLM_GFX906_F105R3_M1_STAGED_AR=1 -e VLLM_GFX906_FORCE_PCIE_CUSTOM_AR=1 -e VLLM_GFX906_POSTED_GEMMA=1 --mount type=bind,src=/home/ai/qwen38-release-retests-20261026/mi50-fp16-tp4-mtp0-r2/cache/torchinductor,dst=/tmp/torchinductor_root --mount type=bind,src=/home/ai/qwen38-release-retests-20261026/mi50-fp16-tp4-mtp0-r2/cache/vllm,dst=/root/.cache/vllm --mount type=bind,src=/home/ai/qwen38-release-retests-20261026/mi50-fp16-tp4-mtp0-r2/cache/.triton,dst=/root/.triton --mount type=bind,src=/usr/share/ollama/localaiservers-vnext/models/Qwen3.8-27B-1d4bf0f2ff6012fd82039f2fa52739d0dd7c60c0,dst=/opt/local-models/Qwen3.8-27B,readonly --mount type=bind,src=/home/ai/qwen38-release-retests-20261026/mi50-fp16-tp4-mtp0-r2/cache/huggingface,dst=/root/.cache/huggingface --mount type=bind,src=/home/ai/qwen38-release-retests-20261026/mi50-fp16-tp4-mtp0-r2,dst=/runwork --entrypoint /opt/vnext/profile/container_entrypoint.sh sha256:5c4e7b7a071d89eee0e8941aa9f9a857b687864ee7bb5d9d59eb7cc50ff48c04
