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

Fix GPU OOM (#6564)

Browse Source 
Co-authored-by: michael <michael.zhang@amd.com>
This commit is contained in:
kk
2025-05-25 07:38:39 +08:00
committed by GitHub
parent 24c035f2e3
commit 7a5e6ce1cb
8 changed files with 15 additions and 16 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
.github/workflows/pr-test-amd.yml vendored
View File

@@ -138,11 +138,6 @@ jobs:
run: |
bash scripts/amd_ci_exec.sh python3 -m unittest test_bench_serving.TestBenchServing.test_offline_throughput_non_stream_small_batch_size
- name: Benchmark online latency (EAGLE)
timeout-minutes: 15
run: |
bash scripts/amd_ci_exec.sh python3 -m unittest test_bench_serving.TestBenchServing.test_online_latency_eagle
performance-test-1-gpu-part-2-amd:
if: (github.repository == 'sgl-project/sglang' || github.event_name == 'pull_request') &&
github.event.pull_request.draft == false