b717dc17a3
<!-- Thanks for sending a pull request! BEFORE SUBMITTING, PLEASE READ https://docs.vllm.ai/en/latest/contributing/overview.html --> ### What this PR does / why we need it? Update CI for GLM-5 configuration on vllm-ascend/releases/v0.18.0 branch 在0.18.0版本上对glm5-w4a8做测试 ### Does this PR introduce _any_ user-facing change? <!-- Note that it means *any* user-facing change including all aspects such as API, interface or other behavior changes. Documentation-only updates are not considered user-facing changes. --> ### How was this patch tested? <!-- CI passed with new added/existing test. If it was tested in a way different from regular unit tests, please clarify how you tested step by step, ideally copy and paste-able, so that other reviewers can test and check, and descendants can verify in the future. If tests were not added, please describe why they were not added and/or why it was difficult to add. --> --------- Signed-off-by: yangjiuhua <y00845194@china.huawei.com> Co-authored-by: yangjiuhua <y00845194@china.huawei.com>
79 lines
2.0 KiB
YAML
79 lines
2.0 KiB
YAML
# ==========================================
|
|
# Shared Configurations
|
|
# ==========================================
|
|
|
|
_envs: &envs
|
|
HCCL_BUFFSIZE: "1024"
|
|
SERVER_PORT: "DEFAULT_PORT"
|
|
HCCL_OP_EXPANSION_MODE: "AIV"
|
|
OMP_PROC_BIND: "false"
|
|
OMP_NUM_THREADS: "1"
|
|
PYTORCH_NPU_ALLOC_CONF: "expandable_segments:True"
|
|
_server_cmd: &server_cmd
|
|
- "--enable-expert-parallel"
|
|
- "--tensor-parallel-size"
|
|
- "16"
|
|
- "--data-parallel-size"
|
|
- "1"
|
|
- "--port"
|
|
- "$SERVER_PORT"
|
|
- "--max-model-len"
|
|
- "16384"
|
|
- "--max-num-batched-tokens"
|
|
- "4096"
|
|
- "--trust-remote-code"
|
|
- "--gpu-memory-utilization"
|
|
- "0.95"
|
|
- "--max-num-seqs"
|
|
- "8"
|
|
- "--quantization"
|
|
- "ascend"
|
|
- "--async-scheduling"
|
|
- "--additional-config"
|
|
- '{"fuse_muls_add": true, "multistream_overlap_shared_expert": false, "ascend_compilation_config": {"enable_npugraph_ex": true}}'
|
|
- "--speculative-config"
|
|
- '{"num_speculative_tokens": 3, "method": "deepseek_mtp"}'
|
|
|
|
_special_dependencies: &special_dependencies
|
|
transformers: "5.2.0"
|
|
|
|
_benchmarks: &benchmarks
|
|
acc:
|
|
case_type: accuracy
|
|
dataset_path: vllm-ascend/gsm8k-lite
|
|
request_conf: vllm_api_general_chat
|
|
dataset_conf: gsm8k/gsm8k_gen_0_shot_cot_chat_prompt
|
|
max_out_len: 8192
|
|
batch_size: 8
|
|
baseline: 95
|
|
threshold: 5
|
|
perf:
|
|
case_type: performance
|
|
dataset_path: vllm-ascend/GSM8K-in3500-bs400
|
|
request_conf: vllm_api_stream_chat
|
|
dataset_conf: gsm8k/gsm8k_gen_0_shot_cot_str_perf
|
|
num_prompts: 16
|
|
max_out_len: 1500
|
|
batch_size: 8
|
|
request_rate: 0
|
|
baseline: 1
|
|
threshold: 0.97
|
|
|
|
# ==========================================
|
|
# ACTUAL TEST CASES
|
|
# ==========================================
|
|
|
|
test_cases:
|
|
- name: "GLM-5-TP16-DP1-decodegraph"
|
|
model: "Eco-Tech/GLM-5-w4a8"
|
|
special_dependencies: *special_dependencies
|
|
envs:
|
|
<<: *envs
|
|
server_cmd: *server_cmd
|
|
server_cmd_extra:
|
|
- "--compilation-config"
|
|
- '{"cudagraph_capture_sizes": [4,8,16,32,64,128,256,512], "cudagraph_mode": "FULL_DECODE_ONLY"}'
|
|
benchmarks:
|
|
<<: *benchmarks
|
|
|