59 lines
2.4 KiB
Bash
59 lines
2.4 KiB
Bash
#!/usr/bin/env bash
|
|
|
|
set -euo pipefail
|
|
|
|
OUTPUT_ROOT="${OUTPUT_ROOT:-$(pwd)/artifacts/flashattn-smoke}"
|
|
VENV_ROOT="${VENV_ROOT:-/tmp/wjh/venvs/vllm-0.20.0-cu129-profiler-v1}"
|
|
VLLM_SOURCE="${VLLM_SOURCE:-/home/admin/cpfs/wjh/agentic-kv/third_party/vllm_v20_build}"
|
|
MODEL="${MODEL:-/home/admin/cpfs/wjh/models/Qwen/Qwen3-30B-A3B}"
|
|
LOG_DIR="${OUTPUT_ROOT}/logs"
|
|
PROVENANCE_DIR="${OUTPUT_ROOT}/provenance"
|
|
|
|
mkdir -p "${LOG_DIR}" "${PROVENANCE_DIR}"
|
|
exec > >(tee -a "${LOG_DIR}/smoke.log") 2>&1
|
|
|
|
if [[ -z "${CUDA_VISIBLE_DEVICES:-}" ]]; then
|
|
echo "ERROR: CUDA_VISIBLE_DEVICES must contain the fleet-allocated GPU" >&2
|
|
exit 1
|
|
fi
|
|
IFS=',' read -r -a GPU_IDS <<< "${CUDA_VISIBLE_DEVICES}"
|
|
if [[ "${#GPU_IDS[@]}" -ne 1 ]]; then
|
|
echo "ERROR: expected exactly one GPU, got ${CUDA_VISIBLE_DEVICES}" >&2
|
|
exit 1
|
|
fi
|
|
|
|
echo "PROFILE_LAUNCH_ECHO host=$(hostname) gpu=${CUDA_VISIBLE_DEVICES} model=${MODEL} runtime=vLLM-0.20.0+cu129 operator=FlashAttention3 tp_local_shapes=1,2,4 specs=q128,4q1s128,q128_4q1s128 dtype=BF16 block=16 output=${OUTPUT_ROOT} expected_wall=3-8m hard_wall=900s hard_gpu_cap=0.15_H20h"
|
|
date -u +"START_UTC=%Y-%m-%dT%H:%M:%SZ"
|
|
nvidia-smi --query-gpu=index,name,driver_version,memory.used,utilization.gpu --format=csv,noheader
|
|
|
|
test -x "${VENV_ROOT}/bin/python"
|
|
test -f "${VLLM_SOURCE}/benchmarks/attention_benchmarks/runner.py"
|
|
test -f "${MODEL}/config.json"
|
|
test -f profile_vllm020_flashattn.py
|
|
|
|
git rev-parse HEAD > "${PROVENANCE_DIR}/aituner.commit"
|
|
git -C "${VLLM_SOURCE}" rev-parse HEAD > "${PROVENANCE_DIR}/vllm-source.commit"
|
|
sha256sum profile_vllm020_flashattn.py run_flashattn_smoke.sh \
|
|
> "${PROVENANCE_DIR}/source.sha256"
|
|
uv pip freeze --python "${VENV_ROOT}/bin/python" \
|
|
> "${PROVENANCE_DIR}/pip-freeze.txt"
|
|
nvidia-smi --query-gpu=index,uuid,name,driver_version,memory.total \
|
|
--format=csv,noheader > "${PROVENANCE_DIR}/gpus.csv"
|
|
|
|
timeout --signal=TERM --kill-after=30s 780 \
|
|
"${VENV_ROOT}/bin/python" profile_vllm020_flashattn.py \
|
|
--vllm-source "${VLLM_SOURCE}" \
|
|
--model "${MODEL}" \
|
|
--output "${OUTPUT_ROOT}/raw/flashattn-smoke.json" \
|
|
--tp 1 2 4 \
|
|
--batch-specs q128 4q1s128 q128_4q1s128 \
|
|
--warmup-iters 3 \
|
|
--repeats 5
|
|
|
|
test -s "${OUTPUT_ROOT}/raw/flashattn-smoke.json"
|
|
sha256sum "${OUTPUT_ROOT}/raw/flashattn-smoke.json" \
|
|
"${PROVENANCE_DIR}"/* > "${OUTPUT_ROOT}/artifacts.sha256"
|
|
nvidia-smi --query-gpu=index,name,memory.used,utilization.gpu --format=csv,noheader
|
|
date -u +"END_UTC=%Y-%m-%dT%H:%M:%SZ"
|
|
echo "FLASHATTN_SMOKE_COMPLETE"
|