biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[Benchmark] Cleanup deprecated nightly benchmark and adjust the docstring for performance benchmark (#25786)

Browse Source 
Signed-off-by: KuntaiDu <kuntai@uchicago.edu>
This commit is contained in:
Kuntai Du
2025-10-29 21:43:37 -07:00
committed by GitHub
parent b5d70751d8
commit 8bff831f0a
29 changed files with 10 additions and 1289 deletions
Download Patch File Download Diff File Expand all files Collapse all files

26
.buildkite/performance-benchmarks/tests/latency-tests-cpu.json Normal file
View File

@@ -0,0 +1,26 @@
[
{
"test_name": "latency_llama8B_tp2",
"environment_variables": {
"VLLM_RPC_TIMEOUT": 100000,
"VLLM_ALLOW_LONG_MAX_MODEL_LEN": 1,
"VLLM_ENGINE_ITERATION_TIMEOUT_S": 120,
"VLLM_CPU_SGL_KERNEL": 1,
"VLLM_CPU_KVCACHE_SPACE": 40
},
"parameters": {
"model": "meta-llama/Llama-3.1-8B-Instruct",
"tensor_parallel_size": 2,
"dtype": "bfloat16",
"distributed_executor_backend": "mp",
"block_size": 128,
"trust_remote_code": "",
"disable_log_stats": "",
"enforce_eager": "",
"max_num_batched_tokens": 2048,
"max_num_seqs": 256,
"num_iters_warmup": 5,
"num_iters": 15
}
}
]