49 lines
2.6 KiB
Bash
49 lines
2.6 KiB
Bash
#!/usr/bin/env bash
|
|
|
|
set -euo pipefail
|
|
|
|
OUTPUT_ROOT="${OUTPUT_ROOT:?OUTPUT_ROOT must be set}"
|
|
RUN_DIR="$(pwd -P)"
|
|
PROFILE_DIR="${PROFILE_DIR:-${RUN_DIR%/runs/frontier-fidelity-envelope-v1}/runs/frontier-qwen30-vllm020-profile-v1}"
|
|
VENV_ROOT="${VENV_ROOT:-/tmp/wjh/venvs/vllm-0.20.0-cu129-profiler-v1}"
|
|
PROFILE_HOME="${PROFILE_HOME:-/tmp/wjh}"
|
|
VLLM_SOURCE="${VLLM_SOURCE:-/home/admin/cpfs/wjh/agentic-kv/third_party/vllm_v20_build}"
|
|
FRONTIER_SOURCE="${FRONTIER_SOURCE:-/home/admin/cpfs/wjh/aituner/frontier-t1-dash0-deadc4a}"
|
|
MODEL_ROOT="${MODEL_ROOT:-/home/admin/cpfs/wjh/models/Qwen/Qwen3-30B-A3B}"
|
|
TOKENS_TEXT="${TOKENS:-1 2 4 8 16 24 32 40 48 56 64 72 80 88 96 104 112 120 128}"
|
|
read -r -a TOKENS <<< "${TOKENS_TEXT}"
|
|
export MODEL_ROOT
|
|
export HOME="${PROFILE_HOME}"
|
|
export XDG_CACHE_HOME="${PROFILE_HOME}/.cache"
|
|
export VLLM_CACHE_ROOT="${XDG_CACHE_HOME}/vllm"
|
|
|
|
mkdir -p "${OUTPUT_ROOT}/logs" "${OUTPUT_ROOT}/provenance" "${OUTPUT_ROOT}/profiles"
|
|
exec > >(tee -a "${OUTPUT_ROOT}/logs/linear.log") 2>&1
|
|
IFS=',' read -r -a GPU_IDS <<< "${CUDA_VISIBLE_DEVICES:?a fleet-allocated GPU is required}"
|
|
if [[ "${#GPU_IDS[@]}" -ne 1 ]]; then
|
|
echo "expected exactly one GPU, got ${CUDA_VISIBLE_DEVICES}" >&2
|
|
exit 1
|
|
fi
|
|
|
|
echo "PROFILE_LAUNCH_ECHO host=$(hostname) gpu=${CUDA_VISIBLE_DEVICES} role=linear-kernel-only tp=1,2,4 tokens='${TOKENS[*]}' method=Frontier-RecordFunctionTracer output=${OUTPUT_ROOT} expected_wall=15-35m expected_gpu_cap=1.0_H20h"
|
|
date -u +"START_UTC=%Y-%m-%dT%H:%M:%SZ"
|
|
test "$(git -C "${FRONTIER_SOURCE}" rev-parse HEAD)" = "deadc4a321f0baaa534c6ebd17f974123733cdc2"
|
|
test "$(git -C "${VLLM_SOURCE}" rev-parse HEAD)" = "88d34c6409e9fb3c7b8ca0c04756f061d2099eb1"
|
|
git rev-parse HEAD > "${OUTPUT_ROOT}/provenance/aituner.commit"
|
|
git -C "${FRONTIER_SOURCE}" rev-parse HEAD > "${OUTPUT_ROOT}/provenance/frontier.commit"
|
|
sha256sum "${PROFILE_DIR}/frontier_vllm020_compat.py" "${RUN_DIR}/run_graph_kernel_only_linear.sh" > "${OUTPUT_ROOT}/provenance/source.sha256"
|
|
|
|
cd "${FRONTIER_SOURCE}"
|
|
timeout --signal=TERM --kill-after=30s 2400 \
|
|
"${VENV_ROOT}/bin/python" "${PROFILE_DIR}/frontier_vllm020_compat.py" \
|
|
--disable_ray --num_gpus 1 --output_dir "${OUTPUT_ROOT}/profiles" \
|
|
--device h20 --models qwen3-a3b-30b-moe \
|
|
--num_tensor_parallel_workers 1 2 4 --max_tokens 128 \
|
|
--num_tokens_list "${TOKENS[@]}" --profile_method record_function \
|
|
--precision BF16 --is_moe --yes
|
|
|
|
find "${OUTPUT_ROOT}/profiles" -name linear_op_kernel_only.csv -type f -size +0c -print -quit > "${OUTPUT_ROOT}/provenance/linear-path.txt"
|
|
test -s "${OUTPUT_ROOT}/provenance/linear-path.txt"
|
|
date -u +"END_UTC=%Y-%m-%dT%H:%M:%SZ"
|
|
echo "GRAPH_KERNEL_ONLY_LINEAR_COMPLETE"
|