chenchenghao/sglang
1
0
Fork 0
Code Issues Pull Requests Actions 11 Packages Projects Releases Wiki Activity
10,431 Commits 1 Branch 0 Tags
4a757990a1d37c00a3b6ce9432d18b46d9ea2595
Commit Graph

44 Commits

Author SHA1 Message Date
Xinyuan Tong
4a757990a1 [VLM] Replace decord with torchcodec for video decoding (#20055) 
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Co-authored-by: BakerBunker <17872844+BakerBunker@users.noreply.github.com>
 2026-03-09 19:23:49 +08:00
Ken J
f0c2089597 [vlm][internVL] Support processor and embedding inputs for InternVL (#19127) 2026-02-26 22:46:48 -08:00
Yuhao Yang
479ab7a4e7 model: support Kimi-K2.5 (#17789) 
Co-authored-by: Mick <mickjagger19@icloud.com>
 2026-01-27 10:57:00 +08:00
siyu
62e6a749b0 Skip mm feature pool init to avoid EPD OOM (#16388) 2026-01-23 10:53:45 +08:00
Zaili Wang
6a8f68b6d2 [Fix] fix device orientation for image processor (#15859) 2026-01-22 15:03:10 +08:00
Yuan Luo
6d29d8ab16 [VLM][Reland] Refactor load_mm_data to improve performance (#16152) 
Co-authored-by: luoyuan.luo <luoyuan.luo@antgroup.com>
 2026-01-18 14:11:17 +08:00
Yuan Luo
53846746bf [VLM] Fix CUDA IPC OOM (#16118) 
Co-authored-by: luoyuan.luo <luoyuan.luo@antgroup.com>
 2026-01-07 11:30:35 +08:00
Nan Jiang
7254986342 [VLM] feat: true on policy for vlm + fsdp (#14636) 
Co-authored-by: Xinyuan Tong <115166877+JustinTong0323@users.noreply.github.com>
 2026-01-01 16:54:39 -08:00
Lianmin Zheng
93495dcac9 Revert "[VLM] Refactor load_mm_data to improve performance" (#15911) 2025-12-26 13:43:18 -08:00
Yuan Luo
086813ae8a [VLM] refactor: refactor load_mm_data to improve performance (#14644) 
Co-authored-by: luoyuan.luo <luoyuan.luo@antgroup.com>
 2025-12-26 13:17:53 +08:00
Yuxuan Zhang
f3ba711662 fix: change class name of GLM-ASR (#15772) 2025-12-26 00:15:16 +08:00
Yuxuan Zhang
82f1d6157f [GLM-ASR] GLM-ASR Support (#15570) 
Co-authored-by: Xinyuan Tong <115166877+JustinTong0323@users.noreply.github.com>
 2025-12-22 17:37:55 -08:00
mlmz
1f1f05a85e vlm: refactor engine vlm params and support processor output as input (#14091) 
Co-authored-by: Mick <mickjagger19@icloud.com>
Co-authored-by: zhaochenyang20 <zhaochenyang20@gmail.com>
Co-authored-by: Xinyuan Tong <115166877+JustinTong0323@users.noreply.github.com>
Co-authored-by: BenYao21 <cyao22@asu.edu>
Co-authored-by: minleminzui <minleminzui@gmail.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Co-authored-by: 赵晨阳 <zhaochen20@outlook.com>
 2025-12-20 18:31:24 +08:00
Yuhao Yang
3d42b7e7b0 unified management of environment variables for vlm cuda ipc transport (#14501) 2025-12-18 12:28:06 +08:00
Tianyu Guo
9acb21ae27 feat: support EPD disaggregation (#12263) 
Co-authored-by: liusy58 <liusy58@linux.alibaba.com>
Co-authored-by: ZhengWG <zwg0606@gmail.com>
Co-authored-by: Nicholas <45984215+liusy58@users.noreply.github.com>
Co-authored-by: Shangming Cai <csmthu@gmail.com>
Co-authored-by: Yuhao Yang <47235274+yhyang201@users.noreply.github.com>
 2025-12-14 22:30:08 +08:00
Yuan Luo
630a693081 [VLM] Boost Memory Pool based CUDA IPC (#14123) 
Co-authored-by: luoyuan.luo <luoyuan.luo@antgroup.com>
 2025-12-01 17:17:46 +08:00
jiapingW
0da30dbc20 fix qwen3-omni audio length < 30s (#12674) 
Co-authored-by: canghua <canghua.wjp@alibaba-inc.com>
 2025-11-06 00:05:28 -08:00
kousakawang
7efd8b3d1f [FEAT] Shared mem pool based cuda ipc for multi-modal data transport (#11917) 
Co-authored-by: kousakawang <wanghanpei@bytedance.com>
Co-authored-by: Yuan Luo <4908075+yuan-luo@users.noreply.github.com>
 2025-11-02 16:46:37 +08:00
Zijian Zhang
a8023891f6 model: support NVILA and NVILA Lite (#10399) 2025-10-26 09:58:09 -07:00
Mick
770529a731 model: support deepseek-ocr (#11891) 
Co-authored-by: yhyang201 <47235274+yhyang201@users.noreply.github.com>
Co-authored-by: yhyang201 <yhyang201@gmail.com>
Co-authored-by: Shi Shuai <126407087+shuaills@users.noreply.github.com>
Co-authored-by: Xinyuan Tong <xinyuantong.cs@gmail.com>
 2025-10-24 03:15:17 +08:00
StonyPort
fd389df96e Reduce the image processing latency in VLM (#11541) 
Co-authored-by: qiuxuan.lzw <qiuxuan.lzw@alibaba-inc.com>
 2025-10-16 15:00:03 -07:00
Mick
86b04d25b3 model: qwen3-omni (thinker-only) (#10911) 
Co-authored-by: Xinyuan Tong <xinyuantong.cs@gmail.com>
 2025-10-16 13:20:38 -07:00
ronnie_zheng
095093ee5a [Ascend] optimize Qwen-vl on Ascend (#10556) 
Co-authored-by: wangqihui01 <wangqh10@163.com>
 2025-09-22 17:18:16 -07:00
Kevin Xiang Li
de28f8e741 vlm: remove redundant d2h movement of mm feature tensors (#9987) 
Co-authored-by: Xiang (Kevin) Li <lik@nvidia.com>
 2025-09-17 15:00:39 -07:00
VDV1985
ba861293cf [feat]Ascend NPU Gemma-3-12b and Gemma-3-27b support (#8909) 2025-08-31 00:25:07 -07:00
Mick
1df84ff414 ci: simplify multi-modality tests by using mixins (#9006) 2025-08-16 22:25:02 -07:00
Mick
41d71ca488 fix: fix obsolete qwen-audio processor arg (#9003) 2025-08-09 13:18:36 -07:00
Binyao Jiang
f29aba8c6e Support glm4.1v and glm4.5v (#8798) 
Signed-off-by: Xinyuan Tong <justinning0323@outlook.com>
Signed-off-by: Xinyuan Tong <xinyuantong.cs@gmail.com>
Co-authored-by: Xinyuan Tong <justinning0323@outlook.com>
Co-authored-by: Xinyuan Tong <115166877+JustinTong0323@users.noreply.github.com>
Co-authored-by: Xinyuan Tong <xinyuantong.cs@gmail.com>
Co-authored-by: zRzRzRzRzRzRzR <2448370773@qq.com>
Co-authored-by: Minglei Zhu <mingleizhu1122@gmail.com>
Co-authored-by: Chang Su <csu272@usc.edu>
 2025-08-09 00:59:13 -07:00
Wenchen Lo
ea93079b30 model: adapt mllama4 to VisionAttention (#8512) 
Co-authored-by: root <mickjagger19@icloud.com>
 2025-08-02 00:39:40 -07:00
Chang Su
51c38163c1 model: support Step3V (#8583) 
Signed-off-by: Xinyuan Tong <justinning0323@outlook.com>
Co-authored-by: nnnobody-code <nnnobody@foxmail.com>
Co-authored-by: ispobock <ispobaoke@gmail.com>
Co-authored-by: Qiaolin-Yu <qy254@cornell.edu>
Co-authored-by: Qiaolin-Yu <liin1211@outlook.com>
Co-authored-by: Xinyuan Tong <justinning0323@outlook.com>
Co-authored-by: Xinyuan Tong <115166877+JustinTong0323@users.noreply.github.com>
 2025-07-31 02:41:00 -07:00
Binyao Jiang
59aab76f0a Bug: Fix google gemma3n-mm audio input not working bug (#8365) 2025-07-30 21:23:09 -07:00
Mick
1992ef9ba7 fix: temporarily disable cuda-ipc for mm data tensor (#8431) 
Signed-off-by: Xinyuan Tong <xinyuantong.cs@gmail.com>
Co-authored-by: Xinyuan Tong <xinyuantong.cs@gmail.com>
 2025-07-29 22:42:03 +00:00
Mick
3212c2ad3f vlm: optimize tensor transport (#6003) 
Co-authored-by: Xinyuan Tong <115166877+JustinTong0323@users.noreply.github.com>
 2025-07-26 17:41:01 +08:00
Xinyuan Tong
69adc4f81c fix: retrieve mm token by modality, raise error if none (#8221) 
Signed-off-by: Xinyuan Tong <xinyuantong.cs@gmail.com>
Co-authored-by: Xinyuan Tong <xinyuantong.cs@gmail.com>
 2025-07-22 08:06:35 +08:00
Xinyuan Tong
8430bfe3e9 [Refactor] simplify multimodal data processing (#8107) 
Signed-off-by: Xinyuan Tong <justinning0323@outlook.com>
 2025-07-20 21:43:09 -07:00
Binyao Jiang
b7e951a6db Feat: Support audio in Phi4-mm model (#8048) 2025-07-18 21:03:53 -07:00
Mick
e1020dc588 refactor: simply MultimodalTokens logic (#7924) 2025-07-17 17:59:15 -07:00
Mick
4395c87a9b refactor: unify names of the feature field of MultimodalDataItem (#8075) 2025-07-16 17:52:38 -07:00
Mick
497efe747d Revert "feat: replace Decord with video_reader-rs" (#8077) 2025-07-15 20:04:56 -07:00
kozo
ebff5fcb06 feat: replace Decord with video_reader-rs (#5163) 
Signed-off-by: Xinyuan Tong <justinning0323@outlook.com>
Co-authored-by: Xinyuan Tong <justinning0323@outlook.com>
 2025-07-15 18:17:34 -07:00
Mick
b5e3d6031c vlm: support video as an input modality (#5888) 2025-07-09 23:48:35 -07:00
Xinyuan Tong
3a911b854d Refactor mm processors and Enable mixed modality processing (#7629) 
Signed-off-by: Xinyuan Tong <justinning0323@outlook.com>
 2025-06-30 23:14:48 -07:00
Lianmin Zheng
071a1f51ae [Minor] clean up multimodal processor and tokenizer manager (#7624) 2025-06-29 02:50:14 -07:00
Lianmin Zheng
ce3a3e8783 Move multimodal processors into a separate folder (#7581) 2025-06-27 11:58:24 -07:00