808d00406f
### What this PR does / why we need it? Adds a `check_rank0_process_count` validation step to the DeepSeek-R1-W8A8-HBM nightly single-node test. The check verifies that after the server starts, there is **exactly 1** `vllm serve` process running on rank0. This guards against the regression fixed in #8041 (extra NPU context leaking on device 0), ensuring it does not silently reappear in future releases. #### Changes - **`tests/e2e/nightly/single_node/models/scripts/test_single_node.py`**: Add `run_check_rank0_process_count` async handler. It calls `npu-smi info` for diagnostics, then uses `psutil` to assert exactly one `vllm serve` process exists on rank0. - **`tests/e2e/nightly/single_node/models/configs/DeepSeek-R1-W8A8-HBM.yaml`**: Register `check_rank0_process_count` in the `test_content` list for the HBM test case. Signed-off-by: hfadzxy <starmoon_zhang@163.com>
46 lines
1.2 KiB
YAML
46 lines
1.2 KiB
YAML
# ==========================================
|
|
# ACTUAL TEST CASES
|
|
# ==========================================
|
|
|
|
test_cases:
|
|
- name: "DeepSeek-R1-W8A8-HBM-single"
|
|
model: "vllm-ascend/DeepSeek-R1-W8A8"
|
|
envs:
|
|
HCCL_BUFFSIZE: "1024"
|
|
SERVER_PORT: "DEFAULT_PORT"
|
|
server_cmd:
|
|
- "--quantization"
|
|
- "ascend"
|
|
- "--port"
|
|
- "$SERVER_PORT"
|
|
- "--data-parallel-size"
|
|
- "8"
|
|
- "--data-parallel-size-local"
|
|
- "8"
|
|
- "--data-parallel-rpc-port"
|
|
- "13389"
|
|
- "--tensor-parallel-size"
|
|
- "2"
|
|
- "--enable-expert-parallel"
|
|
- "--seed"
|
|
- "1024"
|
|
- "--max-num-seqs"
|
|
- "32"
|
|
- "--max-model-len"
|
|
- "6000"
|
|
- "--max-num-batched-tokens"
|
|
- "6000"
|
|
- "--trust-remote-code"
|
|
- "--gpu-memory-utilization"
|
|
- "0.92"
|
|
- "--no-enable-prefix-caching"
|
|
- "--reasoning-parser"
|
|
- "deepseek_r1"
|
|
- "--enforce-eager"
|
|
- "--additional-config"
|
|
- '{"ascend_scheduler_config": {"enabled": false}, "torchair_graph_config": {"enabled": false, "enable_multistream_shared_expert": false}}'
|
|
test_content:
|
|
- completion
|
|
- check_rank0_process_count
|
|
benchmarks:
|