Launch Qwen30 fixed pressure comparison

This commit is contained in:
2026-07-19 02:25:15 +08:00
parent 7ea9635878
commit c8383c9c4c
3 changed files with 196 additions and 1 deletions

View File

@@ -21,6 +21,14 @@ SERVER_READY_ATTEMPTS="${SERVER_READY_ATTEMPTS:-300}"
IDLE_GPU_MEMORY_TOLERANCE_MIB="${IDLE_GPU_MEMORY_TOLERANCE_MIB:-16}"
RESUME_VALID_CELLS="${RESUME_VALID_CELLS:-false}"
PORT="${BASE_PORT:-8300}"
REQUEST_COUNT="$(wc -l < "${TRACE_ROOT}/tp1/private/real_requests.jsonl")"
for tp in 2 4; do
[[ "$(wc -l < "${TRACE_ROOT}/tp${tp}/private/real_requests.jsonl")" == "${REQUEST_COUNT}" ]] || {
echo "ERROR: TP-specific request counts differ" >&2
exit 1
}
done
case "${PREFIX_CACHING}" in
true|false) ;;
@@ -186,7 +194,7 @@ run_tp_wave() {
}
{
printf '%s\n' "REAL_LAUNCH_ECHO host=dash0 model=Qwen3-30B-A3B engine=vLLM-0.20.0+cu129 dtype=BF16 case=${CASE_NAME} traces=${TRACE_ROOT}/tp{1,2,4}/private/real_requests.jsonl prefix=${PREFIX_CACHING} requests=129 transform=t_prime=t/TP surface=TP{1,2,4}xMNS{8,16,32,64} trials=3 fresh_server=true resume_valid_cells=${RESUME_VALID_CELLS} idle_gpu_memory_tolerance_mib=${IDLE_GPU_MEMORY_TOLERANCE_MIB} metrics=mean,p90(TTFT,TPOT-if-OSL-gt-1,E2E) expected_cost=13_H20-GPUh_nominal__41_H20-GPUh_max output=${OUT}/real"
printf '%s\n' "REAL_LAUNCH_ECHO host=dash0 model=Qwen3-30B-A3B engine=vLLM-0.20.0+cu129 dtype=BF16 case=${CASE_NAME} traces=${TRACE_ROOT}/tp{1,2,4}/private/real_requests.jsonl prefix=${PREFIX_CACHING} requests=${REQUEST_COUNT} transform=t_prime=t/TP surface=TP{1,2,4}xMNS{8,16,32,64} trials=3 fresh_server=true resume_valid_cells=${RESUME_VALID_CELLS} idle_gpu_memory_tolerance_mib=${IDLE_GPU_MEMORY_TOLERANCE_MIB} metrics=mean,p90(TTFT,TPOT-if-OSL-gt-1,E2E) expected_cost=13_H20-GPUh_nominal__41_H20-GPUh_max output=${OUT}/real"
date -u +START_UTC=%Y-%m-%dT%H:%M:%SZ
mkdir -p "${OUT}/provenance" "${FLASHINFER_SHARED_WORKSPACE}"
sha256sum "${BASH_SOURCE[0]}" "${RUNNER}" "${CLIENT}" "${PREFILL_CLIENT}" \