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

4
.buildkite/nightly-benchmarks/tests/latency-tests.json
View File

@@ -2,7 +2,7 @@
{
"test_name": "latency_llama8B_tp1",
"parameters": {
"model": "meta-llama/Meta-Llama-3-8B",
"model": "meta-llama/Meta-Llama-3.1-8B-Instruct",
"tensor_parallel_size": 1,
"load_format": "dummy",
"num_iters_warmup": 5,
@@ -12,7 +12,7 @@
{
"test_name": "latency_llama70B_tp4",
"parameters": {
"model": "meta-llama/Meta-Llama-3-70B-Instruct",
"model": "meta-llama/Meta-Llama-3.1-70B-Instruct",
"tensor_parallel_size": 4,
"load_format": "dummy",
"num-iters-warmup": 5,