[Bugfix] Fix CUDA graph replay issues in trtllm_mla draft_extend (#21987)

Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
This commit is contained in:
Khoa Pham
2026-04-03 01:45:13 -07:00
committed by GitHub
co-authored by Claude Opus 4.6
parent 4f84ce5807
commit cd75d54fc5
2 changed files with 15 additions and 14 deletions
+2 -1
View File
@@ -25,6 +25,7 @@ on:
- 'nightly-test-multimodal-server-2-gpu'
- 'nightly-test-perf-4-gpu-b200'
- 'nightly-test-perf-8-gpu-b200'
- 'nightly-test-specialized-8-gpu-b200'
- 'nightly-test-kernel-1-gpu-h100'
- 'nightly-test-diffusion-comparison'
- 'nightly-test-kernel-8-gpu-h200'
@@ -626,7 +627,7 @@ jobs:
# Specialized B200 tests - 8 GPU, for specific backends and configs
nightly-test-specialized-8-gpu-b200:
if: github.repository == 'sgl-project/sglang' && (inputs.job_filter == '' || inputs.job_filter == 'all' || inputs.job_filter == 'nightly-test-perf-8-gpu-b200')
if: github.repository == 'sgl-project/sglang' && (inputs.job_filter == '' || inputs.job_filter == 'all' || inputs.job_filter == 'nightly-test-perf-8-gpu-b200' || inputs.job_filter == 'nightly-test-specialized-8-gpu-b200')
runs-on: 8-gpu-b200
env:
RUNNER_LABELS: 8-gpu-b200