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

[CI] Fix crashes of performance benchmark (#7500)

Browse Source
This commit is contained in:
Kuntai Du
2024-08-16 08:08:45 -07:00
committed by GitHub
parent 9587b050fb
commit 6fc5b0f249
5 changed files with 21 additions and 36 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
.buildkite/nightly-benchmarks/tests/serving-tests.json
View File

@@ -3,7 +3,7 @@
"test_name": "serving_llama8B_tp1_sharegpt",
"qps_list": [1, 4, 16, "inf"],
"server_parameters": {
"model": "meta-llama/Meta-Llama-3-8B",
"model": "meta-llama/Meta-Llama-3.1-8B-Instruct",
"tensor_parallel_size": 1,
"swap_space": 16,
"disable_log_stats": "",
@@ -11,7 +11,7 @@
"load_format": "dummy"
},
"client_parameters": {
"model": "meta-llama/Meta-Llama-3-8B",
"model": "meta-llama/Meta-Llama-3.1-8B-Instruct",
"backend": "vllm",
"dataset_name": "sharegpt",
"dataset_path": "./ShareGPT_V3_unfiltered_cleaned_split.json",
@@ -22,7 +22,7 @@
"test_name": "serving_llama70B_tp4_sharegpt",
"qps_list": [1, 4, 16, "inf"],
"server_parameters": {
"model": "meta-llama/Meta-Llama-3-70B-Instruct",
"model": "meta-llama/Meta-Llama-3.1-70B-Instruct",
"tensor_parallel_size": 4,
"swap_space": 16,
"disable_log_stats": "",
@@ -30,7 +30,7 @@
"load_format": "dummy"
},
"client_parameters": {
"model": "meta-llama/Meta-Llama-3-70B-Instruct",
"model": "meta-llama/Meta-Llama-3.1-70B-Instruct",
"backend": "vllm",
"dataset_name": "sharegpt",
"dataset_path": "./ShareGPT_V3_unfiltered_cleaned_split.json",
@@ -60,7 +60,7 @@
"test_name": "serving_llama70B_tp4_sharegpt_specdecode",
"qps_list": [2],
"server_parameters": {
"model": "meta-llama/Meta-Llama-3-70B-Instruct",
"model": "meta-llama/Meta-Llama-3.1-70B-Instruct",
"disable_log_requests": "",
"tensor_parallel_size": 4,
"swap_space": 16,
@@ -70,7 +70,7 @@
"use_v2_block_manager": ""
},
"client_parameters": {
"model": "meta-llama/Meta-Llama-3-70B-Instruct",
"model": "meta-llama/Meta-Llama-3.1-70B-Instruct",
"backend": "vllm",
"dataset_name": "sharegpt",
"dataset_path": "./ShareGPT_V3_unfiltered_cleaned_split.json",