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

[CI] the readability of benchmarking and prepare for dashboard (#5571)

Browse Source 
[CI] Improve the readability of performance benchmarking results and prepare for upcoming performance dashboard (#5571)
This commit is contained in:
Kuntai Du
2024-06-17 11:41:08 -07:00
committed by GitHub
parent ab66536dbf
commit 9e4e6fe207
8 changed files with 213 additions and 111 deletions
Download Patch File Download Diff File Expand all files Collapse all files

35
.buildkite/nightly-benchmarks/tests/throughput-tests.json Normal file
View File

@@ -0,0 +1,35 @@
[
{
"test_name": "throughput_llama8B_tp1",
"parameters": {
"model": "meta-llama/Meta-Llama-3-8B",
"tensor_parallel_size": 1,
"load_format": "dummy",
"dataset": "./ShareGPT_V3_unfiltered_cleaned_split.json",
"num_prompts": 200,
"backend": "vllm"
}
},
{
"test_name": "throughput_llama70B_tp4",
"parameters": {
"model": "meta-llama/Meta-Llama-3-70B-Instruct",
"tensor_parallel_size": 4,
"load_format": "dummy",
"dataset": "./ShareGPT_V3_unfiltered_cleaned_split.json",
"num_prompts": 200,
"backend": "vllm"
}
},
{
"test_name": "throughput_mixtral8x7B_tp2",
"parameters": {
"model": "mistralai/Mixtral-8x7B-Instruct-v0.1",
"tensor_parallel_size": 2,
"load_format": "dummy",
"dataset": "./ShareGPT_V3_unfiltered_cleaned_split.json",
"num_prompts": 200,
"backend": "vllm"
}
}
]