 Mohammad Miadh Angkad
|
7b1a20344c
|
Re-enable SM90 FlashInfer allreduce fusion with safe backend defaults (#28789)
|
2026-06-23 01:29:19 -07:00 |
|
|
Liangsheng Yin
|
854c688121
|
[Spec] Unify decode KV-commit bookkeeping across spec-v2 workers (#28754)
|
2026-06-23 00:53:05 -07:00 |
|
|
cctryandcctry
|
743ce88bc5
|
Fix flaky optimistic prefill retry test (#28995)
Co-authored-by: cctry <cctry@fb.com>
|
2026-06-23 00:18:01 -07:00 |
|
|
Mick
|
219742c394
|
[diffusion] optimize: optimize realtime causal attention fastpath (#28760)
|
2026-06-23 15:15:30 +08:00 |
|
|
Cheng Wan
|
c4376aaa88
|
[Refactor] Remove dead out_cache_loc_swa buffers (#28968)
|
2026-06-23 00:03:30 -07:00 |
|
|
vikram singh shekhawatandClaude Sonnet 4.6
|
e63b57da0b
|
[Fix] model init / XPU / transformers-v5 / bench-image fixes (#28292)
Co-authored-by: Claude Sonnet 4.6 (1M context) <noreply@anthropic.com>
|
2026-06-23 12:58:13 +08:00 |
|
|
Liangsheng Yin
|
4740f23e1f
|
Revert "[server_args] compute mem_fraction_static after dp chunked-prefill division" (#28991)
|
2026-06-22 20:48:16 -07:00 |
|
|
Yuan Luoandluoyuan.luo
|
abb0717174
|
[CI] Fix lint brought by #27527 (#28988)
Co-authored-by: luoyuan.luo <luoyuan.luo@antgroup.com>
|
2026-06-22 20:40:06 -07:00 |
|
|
Chetan Kumar Verma
|
6cd8d2869b
|
Vectorize _create_custom_4d_mask in CustomQwen2Decoder (#27527)
|
2026-06-23 10:56:35 +08:00 |
|
|
|
62f7ffc492
|
feat: add Mooncake group semantics (#26574)
Co-authored-by: Zhiqiang Xie <xiezhq@stanford.edu>
Co-authored-by: Teng Ma <sima.mt@alibaba-inc.com>
|
2026-06-22 19:38:58 -07:00 |
|
|
Terry-UVandhnyls2002
|
a17753e449
|
Fix EAGLE draft graph seq_lens_sum padding (#26880)
Co-authored-by: hnyls2002 <lsyincs@gmail.com>
|
2026-06-22 18:00:25 -07:00 |
|
|
Xinyuan Tong
|
de3ec2c437
|
[server_args] compute mem_fraction_static after dp chunked-prefill division (#28884)
|
2026-06-22 17:59:05 -07:00 |
|
|
Brayden Zhong
|
ba9d5aed98
|
Fix nightly CI test for Kimi K2.5 INT4 + H200 (#28746)
|
2026-06-23 00:27:33 +00:00 |
|
|
Liangsheng Yin
|
d70726a31a
|
Revert "[server_args] fix FA4 page_size auto-force for combined --attention-backend fa4" (#28972)
|
2026-06-22 17:01:37 -07:00 |
|
|
Ting SUN
|
e00703bb2a
|
fix(frontend): return 400 for missing completions json_schema (#28090)
Signed-off-by: Ting Sun <suntcrick@gmail.com>
|
2026-06-22 15:47:05 -07:00 |
|
|
|
6c212a5d6b
|
[server_args] fix FA4 page_size auto-force for combined --attention-backend fa4 (#28825)
Co-authored-by: Brayden Zhong <b8zhong@uwaterloo.ca>
Co-authored-by: Brayden Zhong <brayden@radixark.ai>
|
2026-06-22 15:35:10 -07:00 |
|
|
Liangsheng Yin
|
770d6b2825
|
[Spec] Add sync-free fast_prefill_plan for EAGLE draft-extend CUDA graph (#28854)
|
2026-06-22 15:15:15 -07:00 |
|
|
Kevin FlansburgandYuhao Yang
|
4f60378ff5
|
Fix Kimi-VL GPU image preprocessing crash on non-RGB images (#28647)
Signed-off-by: Kevin Flansburg <kflansburg@cloudflare.com>
Co-authored-by: Yuhao Yang <47235274+yhyang201@users.noreply.github.com>
|
2026-06-22 14:23:33 -07:00 |
|
|
Maxwill LinandClaude Opus 4.8
|
bbc853df46
|
fix(schedule_batch): trim stop string when EOS matches in the same step (#28802)
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
|
2026-06-22 13:14:00 -07:00 |
|
|
Xinyuan Tong
|
7c23d2255a
|
[minimax-m3] Split 1/4: sparse attention ops + JIT kernels + config foundation (#28712)
|
2026-06-22 13:10:43 -07:00 |
|
|
Alex NailsandClaude Opus 4.7
|
b5e4e289b1
|
[gRPC] Native server: Python bridge entrypoint (2/4) (#23507)
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
|
2026-06-22 13:08:33 -07:00 |
|
|
Wenyao Gao
|
8dc27f6326
|
[MoE] dedup triton_kernels backend quant-arg asserts and fill weight dtype guard (#28689)
|
2026-06-22 13:01:21 -07:00 |
|
|
zijiexiaandClaude Opus 4.8
|
669be5448b
|
[cuda graph] Enable prefill piecewise CUDA graph for Cohere2Vision (text path) (#28686)
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
|
2026-06-22 19:20:14 +00:00 |
|
|
Zhangheng
|
70883cb1b0
|
[UnifiedTree]: Rollback mamba hicache test to direct io backend (#28904)
|
2026-06-22 23:48:48 +08:00 |
|
|
Mick
|
bbe8b7dd8a
|
[diffusion] CI: restore Hunyuan3D-2 image-to-3D (#28781)
|
2026-06-22 23:36:18 +08:00 |
|
|
Lianmin Zheng
|
b28e990161
|
Migrate all ServerArgs fields to Annotated style, reduce add_cli_args by ~2400 lines (#28919)
|
2026-06-22 08:34:37 -07:00 |
|
|
Xiaoyu Zhang
|
6b2c730bf7
|
[codex] Fix DSA indexer in prefill piecewise CUDA graph (#28644)
|
2026-06-22 22:39:21 +08:00 |
|
|
Xiaoyu Zhang
|
b43bd6824f
|
[B300] Enable FlashInfer allreduce for Qwen3-VL MoE (#28786)
|
2026-06-22 22:38:45 +08:00 |
|
|
Thomas Wang
|
cee1caaf47
|
[AMD] Fix nightly-8-gpu-mi35x-deepseek-v4-flash-rocm720 OOM issue (#28941)
|
2026-06-22 07:35:45 -07:00 |
|
|
Thomas Wang
|
04d952ea10
|
[AMD] deepseek-v4 clean env vars (#28920)
|
2026-06-22 07:32:43 -07:00 |
|
|
Mick
|
4923bb93ae
|
[diffusion] CI: fix turbo_wan/flux invisible CI cases (#28913)
|
2026-06-22 21:21:16 +08:00 |
|
|
Lianmin Zheng
|
ad9723af03
|
Clean up CUDA graph capture logs (#28937)
|
2026-06-22 06:15:26 -07:00 |
|
|
Mick
|
ead39d38fc
|
[diffusion] refactor: refactor causal KV local head cache updates (#28888)
|
2026-06-22 21:00:38 +08:00 |
|
|
shihaozhou
|
1adb53f147
|
Fix CP page filtering by request-local position (#28718)
|
2026-06-22 20:47:29 +08:00 |
|
|
Xiaoyu Zhang
|
0c9e775f2c
|
[Diffusion] Fix FastWan2.1 default 480p resolution (#28733)
|
2026-06-22 18:43:24 +08:00 |
|
|
Yuwei An
|
2ce32366a0
|
[Fix][BCG][Spec] Restore EAGLE prefill plumbing dropped by #23906 (#28870)
|
2026-06-22 01:54:54 -07:00 |
|
|
Xinyuan Tong
|
db12bfcdc8
|
[JIT] Add kpool_topk_transform JIT kernel (#28670)
|
2026-06-22 01:04:21 -07:00 |
|
|
Liangsheng Yinandthanhhao98
|
106d2930a6
|
[core] Gate the overlap WAR barrier on forward reads to recover decode throughput (#28363)
Co-authored-by: thanhhao98 <31717833+thanhhao98@users.noreply.github.com>
|
2026-06-22 00:40:56 -07:00 |
|
|
Polisetty V R K Jyothendra VarmaandMa Mingfei
|
62b3c8e177
|
[Intel GPU] Guard tvm_ffi import in dsv4 online mtp module under TYPE_CHECKING to fix import error on XPU (#28531)
Signed-off-by: P V R K Jyothendra Varma <polisetty.v.r.k.jyothendra.varma@intel.com>
Co-authored-by: Ma Mingfei <mingfei.ma@intel.com>
|
2026-06-22 13:56:21 +08:00 |
|
|
Khoa PhamandCursor
|
0642cd5020
|
(chore): bump tokenspeed_mla to 0.1.7 (#28759)
Co-authored-by: Cursor <cursoragent@cursor.com>
|
2026-06-21 21:25:37 -07:00 |
|
|
Lianmin Zheng
|
886b96621d
|
Migrate more server args to annotated style (#28830)
|
2026-06-21 20:50:17 -07:00 |
|
|
cctryandcctry
|
0c065671c9
|
[Spec] Redo: split init_backends; account draft weights in --mem-fraction-static (#28855)
Co-authored-by: cctry <cctry@fb.com>
|
2026-06-21 20:45:16 -07:00 |
|
|
Mick
|
2b2cd21783
|
[diffusion] fix: reject cache-dit with fsdp (#28834)
|
2026-06-22 10:47:40 +08:00 |
|
|
Trevor Morris
|
c0bb04b67f
|
[NVIDIA] Support NVFP4 MoE for DeepSeek-V4 (#25820)
|
2026-06-21 19:35:14 -07:00 |
|
|
|
6779ca8d7f
|
Fix Qwen MoE precision issue with PP and all-reduce fusion (#28619)
Co-authored-by: hjzhang <zhanghjzzz@qq.com>
Co-authored-by: Mohammad Miadh Angkad <176301910+mmangkad@users.noreply.github.com>
|
2026-06-22 08:20:16 +08:00 |
|
|
Liangsheng Yin
|
4f5ff39bc9
|
[Spec] Enable FR-Spec in EAGLE draft-extend CUDA graph by sizing logits buffer from the draft head (#28856)
|
2026-06-21 15:35:57 -07:00 |
|
|
Liangsheng Yin
|
e6722c751b
|
[Feature] Add graceful scheduler shutdown; free hisparse host buffer on exit (#28779)
|
2026-06-21 15:08:10 -07:00 |
|
|
Liangsheng Yin
|
8e890391f5
|
[Spec] Support FlashInfer CUDA graph for EAGLE draft-extend (#28782)
|
2026-06-21 14:46:25 -07:00 |
|
|
Lianmin Zhengandhnyls2002
|
a4d0ff3def
|
[misc] Make NaN-logit sanitization opt-in (default off) (#28829)
Co-authored-by: hnyls2002 <lsyincs@gmail.com>
|
2026-06-21 14:31:35 -07:00 |
|
|
|
7f67965b4d
|
[BugFix] NCCL deadlock in HiCache writing_check by making all_reduce unconditional (#26923)
Co-authored-by: Claude <noreply@anthropic.com>
Co-authored-by: Zhiqiang Xie <xiezhq@stanford.edu>
Co-authored-by: Zhangheng <hzh0425@apache.org>
|
2026-06-22 01:47:44 +08:00 |
|