Commit Graph

9885 Commits

Author SHA1 Message Date
Baizhou Zhang
8698867479 [CI]Add gb200 runner back (#15024) 2025-12-12 20:19:34 -08:00
Kangyan-Zhou
291396544e Add a special label for b200 CI runner that can run kernel tests (#15033) 2025-12-12 19:41:36 -08:00
Shu Wang
665cb02003 Fix regression caused by fa3 block_table (#15009) 2025-12-12 19:11:09 -08:00
Liangsheng Yin
7160283800 Tiny remove the duplicate function in spec v2 (#14957) 2025-12-13 11:08:27 +08:00
Qiaolin Yu
77873343c4 tiny update: use rope kernel in sgl-kernel for amd (#14955) 2025-12-12 18:48:12 -08:00
Lianmin Zheng
267170bf1d Clean up server args and engine startup processes (#15015) 2025-12-12 18:46:07 -08:00
fzyzcjy
313f59ad80 Add soft watchdogs to debug soft hangs (#15023) 2025-12-13 10:41:35 +08:00
fzyzcjy
487cf81a68 Tiny extract SchedulerWatchdog (#15021) 2025-12-13 10:40:32 +08:00
fzyzcjy
df111bc0fe Super tiny add gsp-fast-prepare (#14992) 2025-12-13 09:45:21 +08:00
fzyzcjy
6d2b3324ef Super tiny fix confusing slash_command_handler hint (#14976) 2025-12-13 09:42:50 +08:00
fzyzcjy
8cc77261ec Super tiny remove unused argument (#14966) 2025-12-13 09:41:01 +08:00
Yinghai Lu
d143b02097 [registry] Add a strict mode to model registration (#14933) 2025-12-13 09:25:48 +08:00
Chenxi Li
9b9d21312a Feature/Fix multi lora scheduler blocking issue and evict LoRA None lastly (#14795) 2025-12-12 17:13:05 -08:00
Qiaolin Yu
44fd701732 Tune triton fused moe for the case of glm-4.6-fp8 b200 tp4 (#15020) 2025-12-12 17:04:56 -08:00
Simo Lin
9a56273ad2 [model-gateway] refactor: unify worker management into modular workflow structure (#15010) 2025-12-12 15:25:35 -08:00
Lianmin Zheng
b737a125c5 Update ci permission (#15014) 2025-12-12 14:11:40 -08:00
Lianmin Zheng
1b5e903480 Refactor of http and engine entrypoints to allow custom override (#14869) 2025-12-12 12:01:08 -08:00
Ho-Ren (Jack) Chuang
171b442ad3 Add KV4-capable backend flashmla and update server args (#14989)
Signed-off-by: Ho-Ren (Jack) Chuang <horenchuang@bytedance.com>
2025-12-12 11:50:27 -08:00
Yineng Zhang
4b7b5af36a Revert several PRs (#14958)
Co-authored-by: fzyzcjy <ch271828n@outlook.com>
2025-12-12 11:25:12 -08:00
fzyzcjy
ec242f516e Super tiny extract route_typed_request_once (#14951) 2025-12-12 11:10:10 -08:00
Kangyan-Zhou
b243154614 Fix CI by reverting incorrect metric check logic (#15004) 2025-12-12 10:07:38 -08:00
Simo Lin
526fd0082f [model-gateway] refactor: workflow engine cleanup and minor optimization (#15001) 2025-12-12 09:03:28 -08:00
Simo Lin
56d0ad47f4 [model-gateway] fix: handle workflow deadlock and optimize cycle detection (#15000) 2025-12-12 08:53:45 -08:00
Simo Lin
306e5b8d0b [model-gateway] feat: add DAG parallel execution support and workflow optimization (#14999) 2025-12-12 08:31:12 -08:00
Simo Lin
10c68f6236 [model-gateway] refactor: extract workflow engine to src/workflow module (#14996) 2025-12-12 06:29:12 -08:00
Mick
c7c837cd1d Update CODEOWNERS for multimodal_gen (#14995) 2025-12-12 22:08:16 +08:00
Xiaoyu Zhang
3e1e71575c [diffusion] docker: Tiny fix Docker Hub link in installation documentation (#14987)
Co-authored-by: Mick <mickjagger19@icloud.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
2025-12-12 20:25:36 +08:00
Kevin Li
8fa8d9d7e8 [PD] Add decode PP event loop for PD disaggregation (#14945)
Signed-off-by: Shangming Cai <csmthu@gmail.com>
Co-authored-by: Shangming Cai <csmthu@gmail.com>
2025-12-12 20:15:00 +08:00
Shangming Cai
c8cf1cafdb [1/N] Update doc of Pipeline Parallelism (#14985)
Signed-off-by: Shangming Cai <csmthu@gmail.com>
Co-authored-by: alpha-baby <fujianhao1997@qq.com>
2025-12-12 19:32:52 +08:00
DefTruth
d71baa72dc [diffusion] dependency: upgrade cache-dit for better compatibility (#14534) 2025-12-12 18:52:58 +08:00
Mick
82e33170e1 [diffusion] chore: minor code cleanups and improve logging (#14916) 2025-12-12 18:48:07 +08:00
gongwei-130
94e1251131 enable flashinfer-jit-cache in image build and ci install to speed up model launch (#14959) 2025-12-11 23:20:44 -08:00
Zaili Wang
4dabfbc827 [Fix] suppress remote weight loading engine w/o mooncake installed (#14937) 2025-12-11 23:12:26 -08:00
Sam
d7ed8a8c24 [NVIDIA] Enable TRTLLM BF16 MoE on Blackwell GPUs (#13798) 2025-12-11 22:56:13 -08:00
ZhengdQin
c05d3afb5d [NPU] optimization for dsv3.2 (#14572) 2025-12-12 14:52:16 +08:00
fzyzcjy
edb172e927 Super tiny refactor error.rs logic (#14949) 2025-12-12 14:48:18 +08:00
b8zhong
fe6d38d2fa fix: trtllm mha attention auto-selection on sm120 (#14842)
Co-authored-by: Brayden Zhong <b8zhong@users.noreply.github.com>
2025-12-11 22:35:25 -08:00
b8zhong
dab31e4cc7 direct register custom op for mm_fp4 (#13699)
Co-authored-by: Brayden Zhong <b8zhong@users.noreply.github.com>
2025-12-11 22:33:17 -08:00
fzyzcjy
a7fa31ff17 Super tiny move error.rs (#14944) 2025-12-12 14:25:30 +08:00
fzyzcjy
bd91f8824a Super tiny remove non-updated sgl_router_worker_load (#14888) 2025-12-12 13:19:30 +08:00
fzyzcjy
b47adb807e Tiny add e2e http request arrival metric (#14893) 2025-12-12 13:18:23 +08:00
fzyzcjy
b2b5bdb06e Tiny add router e2e duration histogram (#14892) 2025-12-12 13:18:13 +08:00
JinYan Su
22fe5da13e Fix negative duration panic in token bucket wait time calculation (#14941)
Signed-off-by: xiaguan <751080330@qq.com>
2025-12-11 21:16:47 -08:00
Praneth Paruchuri
1834401e7c [model-gateway] optimize worker selection (#14894) 2025-12-11 21:15:12 -08:00
Prozac614
198c8ecf98 [diffusion] fix: support applying different LoRA adapters to different transformers in multi-transformer pipelines (#14839) 2025-12-12 13:08:57 +08:00
Xuchun Shang
c01b2ee094 [PP] Refactor PP to async mode (#11852)
Signed-off-by: Shangming Cai <csmthu@gmail.com>
Signed-off-by: Xuchun Shang <xuchun.shang@gmail.com>
Co-authored-by: Lianmin Zheng <lianminzheng@gmail.com>
Co-authored-by: Shangming Cai <csmthu@gmail.com>
Co-authored-by: bluecoffee8 <jasperli2002@gmail.com>
Co-authored-by: zhangxiaolei123456 <zhangxiaolei.666@bytedance.com>
Co-authored-by: ybyang <10629930+whybeyoung@users.noreply.github.com>
2025-12-12 12:54:16 +08:00
Peng Zhang
8f5adac8c6 [RL] refactor flash rl weight reload in sglang (#14870)
Co-authored-by: eternally-z <zzywzj@gmail.com>
2025-12-12 12:50:47 +08:00
Zehuan Li
76743a983e [DLLM] Add documentation for diffusion LLMs (#14358)
Co-authored-by: Tiwei Bie <tiwei.btw@antgroup.com>
Co-authored-by: Jinwei Yao <jinweiy@illinois.edu>
2025-12-11 20:29:51 -08:00
Xinyuan Tong
8bf10e71cd remove dpsk3.2 sys prompt (#14923)
Signed-off-by: Xinyuan Tong <xinyuantong.cs@gmail.com>
2025-12-11 20:26:13 -08:00
fzyzcjy
e4873d0439 Super tiny remove sgl_router_active_workers (#14891) 2025-12-11 20:00:55 -08:00