Commit Graph

7039 Commits

Author SHA1 Message Date
YAMY
cfead25bbf [Qwen3.5] mamba slice fix (Prefill TP != Decode TP & decode TP size>1) (#20655)
Co-authored-by: Shangming Cai <csmthu@gmail.com>
2026-03-17 19:30:58 +08:00
AMD-yanfeiwang
966ae87d02 [AMD] avoid correction_bias_dtype dtype convert (#20692) 2026-03-17 02:55:05 -07:00
Liangsheng Yin
5270a06488 [Disagg] Fix health check false-positive in disagg is_fully_idle (#20756) 2026-03-17 17:18:54 +08:00
Duyi-Wang
385a35bd11 [AMD][MORI] Fix MTP crash with FP4/FP8 dispatch and add NEXTN dispatch env vars. (#20647) 2026-03-17 01:13:42 -07:00
Junhao Liu
ee106757df [diffusion] fix: fix Diffusers backend ignores model-specific sampling parameter (#20080)
Co-authored-by: Mick <mickjagger19@icloud.com>
2026-03-17 16:10:46 +08:00
akhilg-nv
9a697ceabb [Fix #20389] Illegal memory access in triton attention for large token counts (#20390) 2026-03-17 00:42:11 -07:00
Ratish P
e3277b3be2 [diffusion]: remove stale offload-manager in LTX2 AV denoising (#20624) 2026-03-17 15:14:00 +08:00
DefTruth
025691cd9e [diffusion] chore: bump up cache-dit & support quant for diffusers backend (#20361) 2026-03-17 12:51:31 +08:00
Rocky Song
079a1fd35e [Bugfix] Fix write-through events not processed when scheduler is idle (#20560) 2026-03-16 21:49:59 -07:00
Shangming Cai
5d5c31c6e4 [PP] Add CP pyobj broadcasting when enable dynamic CPP (#20738) 2026-03-17 12:20:11 +08:00
MMuzzammil1
855ec7017d Add check to provide hicache-storage-backend when enabling kv caching on Decode Side in PD Disaggregation (#20732)
Signed-off-by: Mohd Muzzammil <me.muzzammil@samsung.com>
2026-03-17 11:25:14 +08:00
Hubert Lu
943f34f642 Add NCCL/RCCL pre-warming to reduce P99 TTFT cold-start latency (#20477)
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-16 20:23:14 -07:00
Jay Shaik
e4d06b3db2 Fix /generate JSON serialization for non-finite top_logprobs (#20714) 2026-03-16 20:07:12 -07:00
shuwenn
515b3a323d feat: support human-readable suffixes (25.6k, 1M, 1Mi) for token CLI (#20577) 2026-03-16 20:05:33 -07:00
psaab
9f56b471aa [Network] Use NetworkAddress for dist_init_method and loopback fallbacks (#20657)
Co-authored-by: hnyls2002 <lsyincs@gmail.com>
2026-03-16 19:59:49 -07:00
Jason Yao
4dbec2dd2b [typo] Fix typos in comments and log messages in common.py (#20723) 2026-03-16 19:26:59 -07:00
Qiaolin Yu
7d87a6a071 Fix spec v1 token_ids_logprobs (#20718) 2026-03-16 19:23:28 -07:00
Mick
474a851ae3 [diffusion] fix: fix sampling params incorrectly override in cli (#20689) 2026-03-17 08:48:10 +08:00
Mick
1eea744855 [diffusion] CI: enable UT (#20690) 2026-03-17 07:44:04 +08:00
roikoren755
5ef5806160 [Nemotron] Small reasoning parser fix (#20284) 2026-03-16 13:29:40 -07:00
Bruce Wu
70a6fb53af Enable embedding lookup/lora_a logic for chunked backend (#17692)
Co-authored-by: Bruce Wu <mogicianwu@fb.com>
Co-authored-by: Baizhou Zhang <sobereddiezhang@gmail.com>
Co-authored-by: Ethan (Yusheng) Su <yushengsu.thu@gmail.com>
2026-03-16 11:37:58 -07:00
Douglas Yang
061ec582bf fix: adding teacache.params back to sampling params as intended (#20665) 2026-03-16 11:27:06 -07:00
ybyang
289cbcf482 fix: support PP2+CP8+TP8 (PP with context parallelism) (#19548) 2026-03-16 16:51:47 +00:00
Xiaoyu Zhang
6489f77733 [Diffusion] Fix compile graph broken by flashinfer rope (#20699) 2026-03-16 23:14:27 +08:00
Du Bin
d3c0f4376a Fix AssertionError crash in disagg prefill inflight queue with PP (#20686) 2026-03-16 22:38:59 +08:00
Xiaoyu Zhang
15097c5c3b Release sglang kernel 0.4.0 (#20440)
Co-authored-by: Baizhou Zhang <sobereddiezhang@gmail.com>
2026-03-16 20:34:58 +08:00
sky
3d58cd16d9 [DP Attention] Optimize dp_padding_mode selection for dp_size=1 in extend mode (#20406)
Signed-off-by: wangfakang <fakangwang@gmail.com>
2026-03-16 18:44:42 +08:00
Xun Sun
549fbcc864 [5/N] (Elastic EP) Use GPU P2P to exchange expert weights during EPLB as much as possible (#12068)
Co-authored-by: Hank Han <hanhan.hank@bytedance.com>
Co-authored-by: Hank Han <hanhan7630@outlook.com>
2026-03-16 18:40:58 +08:00
Xiaoyu Zhang
3055b6906d [Diffusion] Document torch.compile graph-break checks in diffusion benchmark skills (#20681) 2026-03-16 17:41:40 +08:00
Mick
485597e651 [diffusion] fix: fix some sampling args passed via cli are omitted (#20630) 2026-03-16 16:55:30 +08:00
Sugar920
895e56097c Add NPU basic function testcases (#19382)
Co-authored-by: cy <chenyang08056032@163.com>
Co-authored-by: Cherry_ming <136634645@qq.com>
2026-03-16 15:09:56 +08:00
shuwenn
42f18fe560 [HiCache] fix: release write-through lock_ref during decode (#20049) 2026-03-16 14:49:31 +08:00
Ke Bao
39336f5812 Precompute swa cache location (#20449) 2026-03-16 14:38:08 +08:00
Zheng Wengang
135af6dc92 [EPD][VLM] support video/audio input (#17824)
Co-authored-by: siyu <liusy58@linux.alibaba.com>
2026-03-16 14:18:21 +08:00
Shangming Cai
738cbde902 [PD] Make pending reqs resolving more robust (#20505)
Signed-off-by: Shangming Cai <csmthu@gmail.com>
2026-03-16 14:12:13 +08:00
pansicheng
97b2a89334 [RadixTree][8/N Refactor]: unify lock interface (#20330) 2026-03-16 11:49:51 +08:00
Liangsheng Yin
f0458e0b49 [Utils] Move network/socket utilities from common.py to network.py (#20646) 2026-03-15 20:35:24 -07:00
Javier Torres
afc71bae3a feat: Add 'none' reasoning effort to ChatCompletionRequest (#20556) 2026-03-15 20:25:48 -07:00
gaopengff
f4393bf3f6 Fix correctness test issue for bench_one_batch (#20650) 2026-03-15 20:05:36 -07:00
Xiaoyu Zhang
e1eb25880f [Diffusion] Add a benchmark for rmsnorm/fuse_add_rmsnorm (#20632) 2026-03-16 09:50:33 +08:00
Zhirui
35c249b4de [OpenAI] Log raw request payload for --log-requests (#20605) 2026-03-15 17:45:00 -07:00
Liangsheng Yin
d852f26cb6 Fix dual-stack socket handling: IPV6_V6ONLY, IPv4-first, is_port_available all-family check (#20643) 2026-03-15 17:17:23 -07:00
jellysnack
53f831691a fix: propagate grammar errors and improve llguidance backend (#20467) 2026-03-15 16:11:18 -07:00
psaab
1145805e7d Fix socket utilities and reserve_port for IPv6 dual-stack support (#20491)
Co-authored-by: hnyls2002 <lsyincs@gmail.com>
2026-03-15 14:29:10 -07:00
Ke Bao
e2be31824f [CI] Add ut coverage tool (#20628) 2026-03-15 21:13:45 +08:00
Yuhao Yang
1c456a0af5 VLM: add Conv2dLayer/Conv3dLayer to fix PyTorch 2.9.1 CuDNN Conv3d (#20282)
Co-authored-by: wili-65535 <wili-65535@users.noreply.github.com>
2026-03-15 19:17:44 +08:00
Kit Fraser-Taliente
7c773ddb0a [Fix] Slice input_embeds to extend_input_len in prepare_for_extend (#20376) 2026-03-15 00:07:05 -07:00
Juan Muneton
7458407437 Fix InternVL and vision attention for non-CUDA backends (e.g. XPU) (#19997)
Co-authored-by: Yang Wang <mr.yang.wang@outlook.com>
2026-03-14 23:24:41 -07:00
shuwenn
1ac6a26464 fix: Nemotron chunk size alias (#20458) 2026-03-14 23:23:39 -07:00
Liangsheng Yin
fc7f9c1de7 Rename --stream-output to --incremental-streaming-output (#20614) 2026-03-14 23:22:33 -07:00