 Lianmin ZhengandYonghao Zhuang
|
3dc93a12ca
|
Improve EPLB dispatch handling and diagnostics (#30646)
Co-authored-by: Yonghao Zhuang <yhzhuang@meta.com>
|
2026-07-10 10:40:19 -07:00 |
|
Zhiyao Jiang
|
789bc3995c
|
[AMD-miles] Bump miles rocm700-mi35x base image and migrate nightly test onto it (#30587)
|
2026-07-10 23:47:06 +08:00 |
|
Zhangheng
|
0299393758
|
[UnifiedTree]: Sync mamba int8 checkpoint (#30626)
|
2026-07-10 23:46:38 +08:00 |
|
Mick
|
559854fe6a
|
[diffusion] docs: sync cookbook and log hygiene (#30791)
|
2026-07-10 22:55:14 +08:00 |
|
Mick
|
7090a49198
|
update codeowners (#30788)
|
2026-07-10 22:35:34 +08:00 |
|
Zhangheng
|
2286e25a21
|
[UnifiedTree]: Sync Replay SSM (#30636)
|
2026-07-10 21:54:59 +08:00 |
|
 Xiaoyu ZhangandClaude Opus 4.8
|
6ed9843b57
|
[Kernel] Introduce sglang.kernels namespace and migrate scattered triton_ops kernels (RFC #29630, Phase 2) (#30044)
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
|
2026-07-10 21:41:08 +08:00 |
|
Xiaoyu Zhang
|
e9493a015c
|
Fix diffusion BCG lifetime and add Z-Image-Turbo CI (#30584)
|
2026-07-10 21:19:59 +08:00 |
|
 
|
94de28764c
|
Fix TiktokenTokenizer missing num_special_tokens_to_add (#30643)
Co-authored-by: Sushil Dubey <sushildubey171@users.noreply.github.com>
Co-authored-by: Mohammad Miadh Angkad <176301910+mmangkad@users.noreply.github.com>
|
2026-07-10 12:37:30 +00:00 |
|
Mohammad Miadh Angkad
|
7045e0fdff
|
Seed sgl-kernel topk sigmoid tests on all backends (#30754)
|
2026-07-10 03:08:15 -07:00 |
|
Xinyuan Tong
|
6174f1cad8
|
[test] Set init-static attrs in mm_process_config mock fixtures (#30766)
|
2026-07-10 03:00:00 -07:00 |
|
BingjiaWang
|
fd19a76237
|
[BUG] fix strip streaming empty-string suffix from DSV4 tool arguments (#29883)
|
2026-07-10 02:05:26 -07:00 |
|
Mohammad Miadh Angkad
|
ecb7fb3989
|
Fix CuTe DSL DSA paged MQA export (#30627)
|
2026-07-10 01:32:58 -07:00 |
|
Liangsheng Yin
|
fef5eda4fb
|
[Refactor] Split DeepSeek-V4 MQALayer into a reusable attention base (#30711)
|
2026-07-10 01:14:03 -07:00 |
|
Mick
|
4a8e1b07a2
|
[diffusion] refactor: reorganize runtime utility and server_args modules (#30447)
|
2026-07-10 15:53:00 +08:00 |
|
 Junjie CaoandZhangheng
|
1d8e3c248b
|
Fix DSV4 HiSparse SWA tail allocation forwarding (#30408)
Co-authored-by: Zhangheng <hzh0425@apache.org>
|
2026-07-10 15:27:02 +08:00 |
|
Xinyuan Tong
|
b76dd0be69
|
Fix Mistral GSM8K chat eval (#27757)
|
2026-07-09 21:08:48 -07:00 |
|
 Richard WangandMick
|
a38cfc6768
|
[diffusion] doc: update cosmos3 cookbook (#27576)
Co-authored-by: Mick <mickjagger19@icloud.com>
|
2026-07-10 11:19:52 +08:00 |
|
zhaozx-cn
|
7966f6be86
|
[NPU] fix npu import cutlass error (#30454)
|
2026-07-10 10:55:31 +08:00 |
|
 
|
edd91cbdd5
|
[diffusion] feat: support action output for cosmos3 (#27168)
Co-authored-by: Kedi Wu <kediw@nvidia.com>
Co-authored-by: Mick <mickjagger19@icloud.com>
|
2026-07-10 10:48:04 +08:00 |
|
 weireweireandweireweire
|
5e3dc5dd5f
|
Fix immediate profiler step range boundary (#30215)
Co-authored-by: weireweire <20922698+weireweire@users.noreply.github.com>
|
2026-07-09 19:47:23 -07:00 |
|
Liangsheng Yin
|
23390589f7
|
[misc] Remove unit test cases that fail the admission criteria (round 3) (#30713)
|
2026-07-09 19:42:51 -07:00 |
|
Liangsheng Yin
|
7b9b2e4798
|
[style] Extract init-static values in memory-cache path (#30710)
|
2026-07-09 19:38:15 -07:00 |
|
Liangsheng Yin
|
ccd2028def
|
[style] Extract init-static values in tokenizer + multimodal path (#30709)
|
2026-07-09 19:36:34 -07:00 |
|
Liangsheng Yin
|
dda61b476e
|
[style] Extract init-static values in forward path (#30708)
|
2026-07-09 19:35:00 -07:00 |
|
Liangsheng Yin
|
b5e75b9423
|
[style] Extract init-static values in scheduler hot path (#30707)
|
2026-07-09 19:33:02 -07:00 |
|
Ma Mingfei
|
073b36853f
|
[CPU] update fla.cpp to support when num_head_v is not multiples of 16 (#30604)
|
2026-07-10 09:21:07 +08:00 |
|
Mick
|
5ce5e1ee3e
|
[Diffusion] Revert CPU AMX optimizations (#30716)
|
2026-07-10 09:09:38 +08:00 |
|
fzyzcjy
|
1e75ba236e
|
Avoid implicit field-based side channel in Scheduler planning (#29408)
|
2026-07-10 08:55:51 +08:00 |
|
 Lianmin Zhengandtanujtiwari1998
|
32c8973ce8
|
Configurable decode retraction order (#30573)
Co-authored-by: tanujtiwari1998 <168470992+tanujtiwari1998@users.noreply.github.com>
|
2026-07-09 17:55:26 -07:00 |
|
fzyzcjy
|
5be9c9f7c6
|
Localize cur_batch field in Scheduler to avoid field-based state access (#29407)
|
2026-07-10 08:55:06 +08:00 |
|
fzyzcjy
|
69368d7593
|
Stop reading cur_batch in is_fully_idle and abort_request (#29406)
|
2026-07-10 08:54:31 +08:00 |
|
 
|
2e66707399
|
Fix pipeline-parallel abort missing in-flight requests in non-current microbatch slots (#29405)
Co-authored-by: burling <3637497+burling@users.noreply.github.com>
Co-authored-by: zhaotyer <89376832+zhaotyer@users.noreply.github.com>
|
2026-07-10 08:53:18 +08:00 |
|
 
|
2c6cd1ef41
|
[Dep] Upgrade flashinfer to 0.6.14 (#29910)
Co-authored-by: Brayden Zhong <b8zhong@uwaterloo.ca>
Co-authored-by: Mohammad Miadh Angkad <176301910+mmangkad@users.noreply.github.com>
|
2026-07-09 17:52:33 -07:00 |
|
Even Zhou
|
b2f9a95867
|
[NPU] use standalone group for moe ep (#29030)
|
2026-07-10 08:49:49 +08:00 |
|
Mohammad Miadh Angkad
|
295f85df08
|
Fix DFlash mamba verify init ordering (#30680)
|
2026-07-09 17:40:12 -07:00 |
|
 Lianmin Zhengandtanujtiwari1998
|
cfc66e05c5
|
[tokenizer] Support pluggable tokenizer worker class in multi-tokenizer mode (#30630)
Co-authored-by: tanujtiwari1998 <168470992+tanujtiwari1998@users.noreply.github.com>
|
2026-07-09 17:31:54 -07:00 |
|
Lianmin Zheng
|
77b7698cad
|
Add tanujtiwari1998 to CI_PERMISSIONS.json (#30649)
|
2026-07-09 17:03:46 -07:00 |
|
  
|
87992eeec4
|
[DeepSeek V2] Reorder dual-stream MoE to main-first to avoid CUDA graph stream explosion (#30460)
Co-authored-by: Cursor <cursoragent@cursor.com>
Co-authored-by: Jiminator <jimmysh341@gmail.com>
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
|
2026-07-09 16:59:39 -07:00 |
|
Liangsheng Yin
|
504570f425
|
[Refactor] Make DeepSeek-V4 attention backend tolerate an absent CPU seq_lens mirror (#30695)
|
2026-07-09 16:39:47 -07:00 |
|
Liangsheng Yin
|
a36c873147
|
[misc] Remove unit test cases that fail the admission criteria (round 2) (#30703)
|
2026-07-09 16:35:59 -07:00 |
|
cctry
|
b86466d54b
|
Make KvVmmArena JIT stub unique per process (#30702)
|
2026-07-09 15:56:26 -07:00 |
|
Liangsheng Yin
|
c53559ba10
|
[misc] Remove unit test cases that fail the admission criteria (#30690)
|
2026-07-09 15:31:28 -07:00 |
|
Baizhou Zhang
|
7e936f690e
|
[Tiny] Fix Lint in #30645 (#30699)
|
2026-07-09 15:30:48 -07:00 |
|
Liangsheng Yin
|
c46b291c77
|
[misc] Add init-static value extraction to the general code style rule (#30701)
|
2026-07-09 15:25:53 -07:00 |
|
Spandan Tiwari
|
40a522203c
|
[Quantization][Bugfix]: Join multi-arg RuntimeError in Quark _check_scheme_supported (#25694)
|
2026-07-09 15:07:14 -07:00 |
|
Spandan Tiwari
|
48d98b7c68
|
[Quantization][bugfix] Correct E8M0 NaN-sentinel detection in e8m0_to_f32 (#25519)
|
2026-07-09 15:02:53 -07:00 |
|
 Spandan TiwariandSpandan Tiwari
|
966350408e
|
[Quantization] Update error message strings with correct framework name in Quark/compressed-tensors (#25467)
Co-authored-by: Spandan Tiwari <12345+spandantiwari@users.noreply.github.com>
|
2026-07-09 14:41:54 -07:00 |
|
Kaixi
|
10bb2eff3d
|
[BCG] Restore Qwen3.5 MRoPE fusion under breakable CUDA graph (#27918)
|
2026-07-09 14:30:05 -07:00 |
|
 DarkSharpnessandClaude Fable 5
|
bda1dc0d95
|
[DSA] Fix top-k v2 emitting invalid indices under tie overflow / inf scores (IMA in FA3 sparse decode) (#30645)
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
|
2026-07-09 14:28:21 -07:00 |
|