EngineX-Hygon/sglang
5
0
Fork 0
Code Issues Pull Requests Actions 7 Projects Releases Wiki Activity

Simplify tests & Fix trtllm custom allreduce registration (#4252)

Browse Source
This commit is contained in:
Lianmin Zheng
2025-03-10 01:24:22 -07:00
committed by GitHub
parent 007f8b3dc2
commit aa957102a9
13 changed files with 30 additions and 211 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
.github/workflows/pr-test.yml vendored
View File

@@ -266,7 +266,7 @@ jobs:
cd test/srt
python3 -m unittest test_bench_one_batch.TestBenchOneBatch.test_moe_tp2_bs1
USE_VLLM_CUSTOM_ALLREDUCE=0 python3 -m unittest test_bench_one_batch.TestBenchOneBatch.test_moe_tp2_bs1
# USE_VLLM_CUSTOM_ALLREDUCE=0 python3 -m unittest test_bench_one_batch.TestBenchOneBatch.test_moe_tp2_bs1
- name: Benchmark single latency + torch.compile (TP=2)
timeout-minutes: 10