Commit Graph

8411 Commits

Author SHA1 Message Date
Yineng Zhang
417e75a60f fix: use 2-gpu-runner for pp 2 NemotronH ut (#16239) 2025-12-31 14:51:33 -08:00
ishandhanani
0500fea965 fix editable install (#16241) 2025-12-31 14:34:54 -08:00
Cheng Wan
2b461c15b4 Update logprob_start_len handling in scheduler (#16240) 2025-12-31 14:11:24 -08:00
Yineng Zhang
5595ae142c docs: fix markdown preview (#16236) 2025-12-31 12:43:57 -08:00
Simo Lin
ace6f3005f ci(benchmark): disable sccache summary annotations and fix tree output (#16233) 2025-12-31 11:05:21 -08:00
Kangyan-Zhou
2da49eec50 Fix XEON docker release workflow (#16107) 2025-12-31 09:47:01 -08:00
Kangyan-Zhou
d65ae0ec7a Use a different concurrency group for release branch testing (#16202) 2025-12-31 09:46:43 -08:00
Simo Lin
60d7279c46 test(tree): add comprehensive unit tests and fix input_char_count bug (#16228) 2025-12-31 07:31:39 -08:00
siyu
abdf65d4f3 Fix OOM by offloading multimodal features to CPU after embedding (#16018) 2025-12-31 23:02:34 +08:00
Huaixin Chang
c1dfbc777b deprecate prefill-round-robin-balance (#16195)
Signed-off-by: Chang Huaixin (OpenAnolis) <changhuaixin@linux.alibaba.com>
Co-authored-by: Liangsheng Yin <lsyincs@gmail.com>
2025-12-31 22:25:33 +08:00
Even Zhou
3b3c5a05c1 [CI/NPU] fix multiple NPU CI issue (#16111) 2025-12-31 21:14:04 +08:00
Muqi Li
2667c857a7 Fix DeepSeekV31's structural tag trigger (#13394) 2025-12-31 21:13:52 +08:00
Kangyan-Zhou
fc643ffbc9 Download missing shards in model weights files when not in CI (#16211) 2025-12-31 20:42:34 +08:00
Yuhao Yang
4280a18a13 [diffusion] CI: add test for cache-dit (#16204)
Co-authored-by: Mick <mickjagger19@icloud.com>
2025-12-31 19:58:10 +08:00
Hexq0210
386e541520 Update document for Ascend NPU (#16214) 2025-12-31 19:03:53 +08:00
Ke Bao
b6267de5ae Upgrade python version in lint ci (#16221) 2025-12-31 18:22:53 +08:00
Baizhou Zhang
e47afa0237 [DP]Fix sync bubble in adjust_num_token_non_padded_for_attn_tp (#16178) 2025-12-31 17:58:18 +08:00
Ethan (Yusheng) Su
5ed384d07b [CI/CD] re-enable lora test (#16187) 2025-12-31 16:32:20 +08:00
Simo Lin
b4ce7a6d71 [model-gateway] cache_aware eliminate String allocations in hot path (#16209) 2025-12-31 00:26:10 -08:00
cen121212
25b48564c3 [NPU][Bugfix] fix Qwen3-VL-30B-A3B-Instruct accuracy loss (#15597) 2025-12-31 15:57:38 +08:00
Bingxu Chen
1c360bf753 [AMD CI] add testcases to unit-test-backend-1-gpu (#16117) 2025-12-30 23:08:45 -08:00
chhnb
3619ec61b4 [diffusion] feat: support multi-frame image output (#15878)
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
2025-12-31 13:50:02 +08:00
Liangsheng Yin
db6b51a838 Add CI_PERMISSION sort hook. (#16200) 2025-12-31 12:15:15 +08:00
Hudson Xing
8a9ca41fda Move log_prefill_stats_late to correct location in PP mode (#15946) 2025-12-31 12:00:24 +08:00
shuwenn
ac11e6a7c5 Add alphabetc1 into CI_PERMISSION (#16198) 2025-12-31 11:31:47 +08:00
roikoren755
47a660d5b9 [NemotronH] PP support (#16172)
Signed-off-by: Roi Koren <roik@nvidia.com>
2025-12-31 11:16:15 +08:00
shuwenn
c0fc7a89e7 [sgl-kernel] fix: make sgl-kernel build respect MAX_JOBS (#15575) 2025-12-31 10:44:45 +08:00
Mick
5bf0d862dd [diffusion] CI: fix generate mode and add cli test (#16174)
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
2025-12-31 09:51:48 +08:00
liupeng374
75b72eb8b2 [cp] assert dsv3.2 cp in pd decode mode (#16156) 2025-12-31 09:24:46 +08:00
Leoyzen
bc8b526eda Fix: Handle empty func_name and None values in GLM MoE detectors (#15754)
Signed-off-by: Xinyuan Tong <xinyuantong.cs@gmail.com>
Co-authored-by: Xinyuan Tong <xinyuantong.cs@gmail.com>
Co-authored-by: Xinyuan Tong <115166877+JustinTong0323@users.noreply.github.com>
2025-12-30 14:32:35 -08:00
Izzy Putterman
3dfff6ae3c Eagle: GPT-OSS Eagle v2 support (#14920)
Signed-off-by: Izzy Putterman <iputterman@nvidia.com>
2025-12-30 14:23:07 -08:00
EkiRui
ad2c1ee352 doc: mooncake store add dummy client support (#16050)
Signed-off-by: Xingrui Yi <yixingrui@linux.alibaba.com>
2025-12-30 12:37:57 -08:00
Simo Lin
9940c6f592 [model-gateway]: ASCII byte comparison and probabilistic timestamp updates (#16181) 2025-12-30 12:28:01 -08:00
Yineng Zhang
00e607111a [Auto Sync] Update request_metrics_exporter.py (20251230) (#16183)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
Co-authored-by: Scott Lee <scottjlee@users.noreply.github.com>
2025-12-30 11:09:41 -08:00
Simo Lin
4bc2f2e0bc [model-gateway][docs] Add Classification API documentation (#16182)
Co-authored-by: Chang Su <chang.s.su@oracle.com>
2025-12-30 10:53:31 -08:00
Roger Young
d17b9e6392 Fusing RMSNormTP in minimax_m2 (#14416)
Co-authored-by: xuebi <xuebi@minimaxi.com>
2025-12-30 10:22:07 -08:00
Liangsheng Yin
ba67e006a7 Refactor speculative algorithm registry. (#16168) 2025-12-31 01:24:22 +08:00
DarkSharpness
45f3ad2f52 [Refactor] Rename CustomOp -> MultiPlatformOp (#16175) 2025-12-31 01:16:32 +08:00
Baizhou Zhang
f35b5da521 [CI] Append test variant name to markdown report header in nightly test (#16166) 2025-12-31 00:09:24 +08:00
Xiaoyu Zhang
733a0c1a37 [Diffusion] Zimage opt with qknorm and flashinfer rope (#16161)
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
2025-12-30 23:39:32 +08:00
Xiaoyu Zhang
b369aaa23f [Diffusion] Refine diffusion profling doc (#16163)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
2025-12-30 23:38:46 +08:00
Ke Bao
b973202526 Split tp model worker init (#16165) 2025-12-30 23:36:03 +08:00
Mufeez Amjad
cbff7ad985 dp-attention: add follow_bootstrap_room + auto load-balance; drop decode_round_robin (#16110) 2025-12-30 22:33:06 +08:00
Liangsheng Yin
4de59d83a1 Reduce stages of pr-test from 4 to 3. (#16173) 2025-12-30 22:21:48 +08:00
Yuhao Yang
39ca57cd28 [diffusion] chore: tiny fix model config (#16159)
Co-authored-by: Mick <mickjagger19@icloud.com>
2025-12-30 22:11:38 +08:00
Mick
3449806727 [diffusion] feat: generalize layer-wise-offload to all supported models (#16150) 2025-12-30 22:06:57 +08:00
Ke Bao
b3817fa93b Split model_worker init function (#16160) 2025-12-30 21:39:11 +08:00
Ke Bao
059428bd8a Tiny remove additional args in init_memory_pool (#16158) 2025-12-30 21:38:06 +08:00
jiapingW
5d200dd8d9 [diffusion] bench: distinguish between video generation and image generation in the bench_serving (#16149) 2025-12-30 21:29:18 +08:00
husf
7f9a3d0609 [docs][NPU]Update model and feature docs support (#16124) 2025-12-30 20:05:40 +08:00