minke.yu/sglang
1
0
Fork 0
Code Issues Pull Requests Actions 12 Packages Projects Releases Wiki Activity
14,605 Commits 2 Branches 0 Tags
bd3b252e0af0e7bfbcc1f329a672a7ee47a36721
Commit Graph
39 Commits
This Branch
This Branch
All Branches
Author SHA1 Message Date
Bingxu Chen e2540188ce [AMD] Clean up DeepSeek-R1-MXFP4 TP2/TP4 MLA GSM8K tests (#27243) 2026-06-21 21:41:19 -07:00
Bingxu Chen fd7874d11b [AMD] Register DP attention test (#28495) 2026-06-21 20:21:41 -07:00
Bingxu Chen 0fc2bc4a8b [AMD] Test DeepSeek V4 FlashMLA backend variants nightly (#28290) 2026-06-16 01:03:26 -07:00
Bingxu Chen 9864059e2b [AMD] Update AITER commit (#28249) 2026-06-15 02:04:34 -07:00
Bingxu ChenandCursor 19c78552dc [AMD] Restrict CI image fallback to versioned tags (#28263) 
Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-06-15 16:08:48 +08:00
Bingxu Chen 1cd5cb1220 [AMD] [CI] Add dsv4 accuracy PR gate to pr-test-amd-rocm720 (#27149) 2026-06-11 23:42:16 -07:00
Bingxu Chen 4704b10d0d [AMD] Update MoRI to v1.2.0 (#27669) 2026-06-09 22:41:53 -07:00
Bingxu Chen 3607cbd65a [AMD] update ROCm AITER commit (#27555) 2026-06-08 08:49:10 -07:00
Bingxu ChenandCursor df6b9c2d9d [AMD] ci: reinstall MoRI if Different from Dockerfile-pinned commit during install_dependency (#27538) 
Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-06-08 16:29:01 +08:00
Bingxu Chen 8c8281801d [AMD] update ROCm AITER commit (#27376) 2026-06-05 03:42:16 -07:00
Bingxu Chen d7013b6537 [AMD] [CI] Remove hardcoded model/cache paths from MI35x nightly tests (#27001) 2026-06-03 02:14:32 -07:00
Bingxu Chen 8e77af1afc [AMD] fix(triton-mla): cap max_kv_splits at 256 on gfx942 (Kimi-K2.6 hang) (#24762) 2026-06-03 00:13:18 -07:00
Bingxu ChenandClaude Opus 4.8 89410b380b [AMD] Pin compressed-tensors==0.15.0 to fix ROCm nightly build (#26879) 
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
 2026-06-01 17:33:00 +08:00
Bingxu ChenandCursor Agent f113ece5cc Revert "improve: combine vit calls for images from different reqs from one batch (#25910)" (#26442) 
Co-authored-by: Cursor Agent <cursoragent@cursor.com>
 2026-05-29 11:13:34 -07:00
Bingxu Chen 5601b7139d [core] Make overlap-schedule WAR barrier CUDA-only (#26646) 2026-05-29 01:02:31 -07:00
Bingxu Chen bdfd5da53e [AMD] AITER Upgrade (#26562) 2026-05-28 02:04:58 -07:00
Bingxu Chenandyctseng0211 6f85957ff2 [AMD] Fix aiter checkout (rocm dockerfile) (#26544) 
Co-authored-by: yctseng0211 <yctseng@amd.com>
 2026-05-28 14:25:01 +08:00
Bingxu ChenandCursor 81663cb5f1 [AMD] [CI] Register MI35x GSM8K nightly tests (#26478) 
Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-05-28 10:31:43 +08:00
Bingxu ChenandCursor e72e3145a0 [AMD] Upgrade AITER (#25896) 
Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-05-21 02:10:43 -07:00
Bingxu ChenandCursor Agent 45cadc215f [AMD][CI] Clean up AMD nightly + pr-test workflows (#25266) 
Co-authored-by: Cursor Agent <cursoragent@cursor.com>
 2026-05-20 23:30:26 -07:00
Bingxu ChenandCursor Agent 2e69266f84 [AMD] avoid aiter re-installing triton in amd_install_dependency (#24981) 
Co-authored-by: Cursor Agent <cursoragent@cursor.com>
 2026-05-11 23:05:16 +08:00
Bingxu ChenandCursor Agent aeb8fefc25 [AMD] Pin cache-dit==1.3.0 in rocm.Dockerfile + AMD CI install script (#24924) 
Co-authored-by: Cursor Agent <cursoragent@cursor.com>
 2026-05-11 22:32:13 +08:00
Bingxu Chenandbingxche 3ffb37789a [AMD] Fix DeepSeek import cascade by supporting both pre- and post-#2958 aiter fused_qk_rmsnorm APIs (#24799) 
Co-authored-by: bingxche <cursoragent@cursor.com>
 2026-05-10 23:41:57 -07:00
Bingxu ChenandCursor Agent 22543b1982 [AMD] DSv4 nightly hotfix + schedule-aware --continue-on-error in AMD CI (#24825) 
Co-authored-by: Cursor Agent <cursoragent@cursor.com>
 2026-05-10 21:46:32 -07:00
Bingxu ChenandYC Yen-Ching Tseng 5eff3c489a [AMD] Deepseek v4 Flash / Pro nightly tests for MI35x ROCm 7.2 (#24203) 
Co-authored-by: YC Yen-Ching Tseng <yctseng@amd.com>
 2026-05-04 00:02:33 -07:00
Bingxu Chen d84470079d [AMD] Fix Grok-2 nightly: avoid multimodal misdetection from auto-populated vision_config (#23383) 2026-04-26 21:54:36 -07:00
Bingxu ChenandYC Yen-Ching Tseng fd88a1c562 [AMD] skip deterministic inference for MLA FP8 test (#23382) 
Co-authored-by: YC Yen-Ching Tseng <yctseng@amd.com>
 2026-04-23 00:43:23 -07:00
Bingxu ChenandClaude Opus 4 2b4eeb8343 [AMD] Restore test_zimage_turbo.py and test_int4fp8_moe.py with __main__ entry (#23455) 
Co-authored-by: Claude Opus 4 (1M context) <noreply@anthropic.com>
 2026-04-22 22:28:20 -07:00
Bingxu Chen 09b1d10d59 [AMD] prepare for MI300x PR runner pool: registry mirror, runner routing, threshold tuning (#23156) 2026-04-21 00:58:23 -07:00
Bingxu ChenHAIgemini-code-assist[bot]
 		69eb95f20c [AMD] Pin peft<0.19 in pyproject_other.toml to fix ROCm CI ImportError (#23161) 
Co-authored-by: HAI <hixiao@gmail.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
 2026-04-19 23:43:56 -07:00
Bingxu Chen ab936ce694 Revert "perf: optimize PCG inductor path for FP8 models (#21734)" (#23159) 
Feel free to PR again.
 2026-04-19 23:32:50 -07:00
Bingxu Chenandbingxche 7ac337df94 [AMD] CI Job Monitor: fix queue time, utilization, and summary metrics (#22274) 
Co-authored-by: bingxche <binxche@amd.com>
 2026-04-16 22:03:37 -07:00
Bingxu Chen 213027951a [AMD] Upgrade Aiter (#22264) 2026-04-10 18:40:43 -07:00
Bingxu Chen 6b96f8341d [AMD] Fix multimodal diffusion test crash on ROCm by falling back to SDPA (#22335) 2026-04-08 22:32:49 -07:00
Bingxu Chenandbingxche de0cfed159 [AMD] Fix DLPack Error in Aiter flydsl GEMM by Detaching MoE Gate Weight (#22262) 
Co-authored-by: bingxche <binxche@amd.com>
 2026-04-07 23:42:10 -07:00
Bingxu Chen 6047d2c690 [AMD] Fix AMD CI monitor GitHub API rate limit exhaustion (#21527) 2026-03-27 02:55:56 -07:00
Bingxu Chen 2e7682414b [AMD] Fix Aiter Prebuild When Releasing ROCm720 Image (#20195) 2026-03-09 21:02:38 -07:00
Bingxu Chen 2d6eb7dff0 [AMD] Add lmsysorg/sglang-daily as A New AMD Daily Image Release Location (#20156) 2026-03-09 01:30:08 -07:00
Bingxu Chen d56fd10cb6 [AMD CI] fix sglang version detection in daily docker image release and init container (#16367) 
https://github.com/sgl-project/sglang/actions/runs/20711245259/job/59453869006?pr=16367 to be fixed in https://github.com/sgl-project/sglang/pull/15663
 2026-01-05 03:22:39 -08:00