Commit Graph

4632 Commits

Author SHA1 Message Date
Liangsheng Yin
196b940aed [3/N] CI refactor: move some manually triggered tests. (#13448) 2025-11-19 23:06:53 +08:00
Zilin Zhu
e197bef5ce [RL] Allow passing tensors of different dtypes for FlattenedTensorBucket (#13413) 2025-11-19 17:24:48 +08:00
ykwd
075ba74dd4 [Doc] Update HiCache and Mooncake docs & Mooncake Setup Error Checking (#12740) 2025-11-19 12:03:27 +08:00
Chen Haozhe
6c2e5fcd91 [feat][Ascend][Mindspore]: support model-impl of mindspore (#9234) 2025-11-19 09:17:47 +08:00
Baizhou Zhang
9f59194f29 [Fix] Fix DeepSeek V3 MTP on B200 (#13548) 2025-11-18 16:30:26 -08:00
b8zhong
92ad2ff9ce Flashinfer TRTLLM-GEN-MoE + Qwen3 (#13489) 2025-11-18 14:18:29 -08:00
Baidu-AIAK
9b64f6f359 [fix] Fixes accuracy issues caused by incorrect use of rope (#13495) 2025-11-18 14:17:33 -08:00
Kangyan-Zhou
c0d1a3383b Remove jet-ai/Jet-Nemotron-2B in nightly text tests as this is constantly failing (#13540) 2025-11-18 13:58:16 -08:00
Glen Liu
d79e12941c Small cleanups related to LoRA weight loading (#13474) 2025-11-18 09:14:34 -08:00
Junrong Lin
518467be64 [Feature] Re:Enable hybrid mem saver (#12962) 2025-11-18 21:29:15 +08:00
Morpheus Guo
7e88b9c128 [BugFix] Accuracy and function Issue when run ptpc quant model (#13157)
Co-authored-by: yuechguo <yuechguo@amd.com>
2025-11-18 01:54:58 -08:00
Zhiqiang Xie
cfcf2758aa [HiCache] Critical fix to host memory double free (#13501)
Co-authored-by: Hao Chen <cighao@gmail.com>
2025-11-18 01:34:23 -08:00
Nicholas
ac81db66c2 [VLM][feat] Support encoder DP for Qwen2.5-VL (#13126)
Co-authored-by: Shangming Cai <csmthu@gmail.com>
Co-authored-by: liusy58 <xiehang.lsy@alibaba-inc.com>
Co-authored-by: Yuan Luo <yuan.luo@hotmail.com>
2025-11-18 16:13:18 +08:00
Cheng Wan
a5ad0069b2 fix: change performance log directory to cache path (#13482)
Co-authored-by: Mick <mickjagger19@icloud.com>
2025-11-18 15:18:43 +08:00
alisonshao
0c96677902 CI: fix NFS EBUSY error in PR test workflow (#13460)
Co-authored-by: Kangyan-Zhou <zky314343421@gmail.com>
Co-authored-by: Mick <mickjagger19@icloud.com>
2025-11-18 13:25:29 +08:00
b8zhong
f33860777c [Piecewise CUDA Graph] Support ModelOpt FP8 (#13094) 2025-11-18 12:46:24 +08:00
Shangming Cai
4c3573e493 [PD] Clarify init method docstrings for kvsender and kvreceiver (#13476) 2025-11-18 12:20:19 +08:00
wingedge
f1be8aa0f2 chore: add an unified server arg for multimodal inputs preprocess config(#12149)
Co-authored-by: bianfeng <bianfeng@pinduoduo.com>
Co-authored-by: Xinyuan Tong <115166877+JustinTong0323@users.noreply.github.com>
2025-11-18 12:18:50 +08:00
Zijian Zhang
aa8ecbda7a model: support JetVLM (#13289) 2025-11-18 12:02:03 +08:00
Binyao Jiang
26ca07469b [GLM4.6v] Relax the constraint of non-user role chat completion message schema for new GLM-v release (#13258) 2025-11-18 10:58:17 +08:00
Binyao Jiang
90c18a16cb [GLM4.6v] Required changes for bumping up to transformer 5.x (#13229) 2025-11-18 10:58:00 +08:00
Minglei Zhu
9846f8ed72 fix MambaPool clear method after refactoring (#13449) 2025-11-18 10:03:45 +08:00
Baizhou Zhang
85ae508e8b Add bfloat16 tuned fused moe config for Dpsk-MTP layer on B200 (#13455) 2025-11-17 17:44:31 -08:00
pansicheng
d879e37f1b Add interface_v1 option for dynamic HiCache backend (#13140)
Co-authored-by: Zhiqiang Xie <xiezhq@stanford.edu>
2025-11-17 17:42:17 -08:00
Kaixi Hou
e389f91dec [NVIDIA] Fix broken fp8 MoE of deepseek v3 (#13264)
Co-authored-by: Baizhou Zhang <sobereddiezhang@gmail.com>
Co-authored-by: Kangyan-Zhou <zky314343421@gmail.com>
2025-11-17 16:13:28 -08:00
Vedant V Jhaveri
aac07bf7fd [Embeddings Performance Testing] Add performance test for embedding models (#12359) 2025-11-17 15:35:18 -08:00
Simo Lin
25acbbc612 Remove verbs from GET endpoint paths to follow REST standards (#13273) 2025-11-17 12:34:36 -08:00
hlu1
a8fcbf6fe3 [Deepseek V3.2] Use torch.compile to speed up torch.cat in nsa (#13022)
Signed-off-by: Hao Lu <14827759+hlu1@users.noreply.github.com>
2025-11-17 12:20:49 -08:00
Liangsheng Yin
6042010964 [2/N] CI refactor: sperate some backend-independent CPU tasks. (#13447) 2025-11-18 02:08:19 +08:00
Mick
ff00b6adbe diffusion: fix loading with local model_path (#13445) 2025-11-18 00:56:30 +08:00
Rain H
c236d05f8c Fix log time stats (#13418) 2025-11-17 23:10:49 +08:00
Carlo Mussolini
df56139226 Adding user defined hooks support (#13217) 2025-11-17 23:07:37 +08:00
kebyn
15db5497d3 [feature] Custom base path on FastAPI server (#5879)
Co-authored-by: lianhu.yin <lianhu.yin@nio.com>
Co-authored-by: kebyn <kebyn@kebyn.cc>
Co-authored-by: Liangsheng Yin <lsyincs@gmail.com>
2025-11-17 22:40:09 +08:00
Mike Qiu
9ba3597d2a Fix cache_tokens calculate issue when retracted (#11900)
Signed-off-by: Michael Qiu <qiudayu.qdy@antgroup.com>
Co-authored-by: Mike_Qiu <qiudayu.qdy@antgroup.com>
2025-11-17 21:25:38 +08:00
Xuchun Shang
80797c2a15 [PD][bug fix] fix memleak when last_batch is none (#13144)
Signed-off-by: Xuchun Shang <xuchun.shang@gmail.com>
Co-authored-by: Shangming Cai <csmthu@gmail.com>
2025-11-17 21:22:20 +08:00
Mick
7afff8fd1a diffusion: fix wan2.2 ti2v num_frames adjust logic (#13379)
Co-authored-by: adarshxs <adarsh.shirawalmath@gmail.com>
Co-authored-by: Adarsh Shirawalmath <114558126+adarshxs@users.noreply.github.com>
2025-11-17 20:53:15 +08:00
AlphaBaby
ac406d4301 fix uneven PP layer indices (#13282)
Co-authored-by: Xuchun Shang <xuchun.shang@linux.alibaba.com>
2025-11-17 19:54:23 +08:00
Yi Zhang
a3e4fe4b41 refactor linear memory pool (#13004) 2025-11-17 16:24:29 +08:00
fzyzcjy
f3e9336dcb Support weight update for blackwell DeepGEMM (#13324) 2025-11-17 15:55:26 +08:00
Teng Ma
290fcd8971 [HiCache] add GPU id to IB dev topo for mooncake storage backend (#13112) 2025-11-17 15:48:29 +08:00
huangtingwei
1dcde53928 [HiCache] support memory_pool_host page head layout (#11644) 2025-11-17 13:45:17 +08:00
Liangsheng Yin
ab63f3c50b [1/N] CI refactor: introduce CI register. (#13345) 2025-11-17 12:21:20 +08:00
Zilin Zhu
147b782352 [RL] re-abort_request when model_update_lock is still locked (#13338) 2025-11-17 12:13:39 +08:00
lixiaolx
d368c7451a (1/n)support context parallel with deepseekv3.2-DSA (#12065) 2025-11-16 20:12:25 -08:00
sglang-bot
7b2fb3d47c chore: bump SGLang version to 0.5.5.post3 (#13366) 2025-11-16 17:55:38 -08:00
Lifu Huang
254f62d879 Support spec decoding when LoRA is applied to target model (#12903) 2025-11-16 13:20:23 -08:00
DangKai
e970892ffa fix import qwenvl error in RL engine (#12874) 2025-11-16 12:01:16 -08:00
b8zhong
d5fa58c4dd fix nightly docker build (#13386) 2025-11-16 11:21:09 -08:00
Liangsheng Yin
e019f233f9 Remove unused code / testcases in lang (#13335) 2025-11-16 22:48:35 +08:00
Xinyuan Tong
b1c688fba2 refactor: cleanup vision attention related codes (#13228)
Signed-off-by: Xinyuan Tong <xinyuantong.cs@gmail.com>
Co-authored-by: alisonshao <54658187+alisonshao@users.noreply.github.com>
Co-authored-by: Mick <mickjagger19@icloud.com>
Co-authored-by: Baizhou Zhang <sobereddiezhang@gmail.com>
Co-authored-by: Kangyan-Zhou <zky314343421@gmail.com>
2025-11-16 22:44:40 +08:00