EngineX-Hygon/sglang
5
0
Fork 0
Code Issues Pull Requests Actions 7 Projects Releases Wiki Activity
4,940 Commits 8 Branches 0 Tags
a38c1497580c3e8af8ce5f9b8aec55e9e161be57
Commit Graph

3327 Commits

Author SHA1 Message Date
wangyu
a38c149758 feat(draft_model): support draft_model for RemoteModelLoader (#6407) 
Signed-off-by: wangyu <wangyu.steph@bytedance.com>
 2025-08-28 16:09:52 -07:00
chenxu140
74dd4249ac [Feature] Support NPUGraph for DeepSeek on Ascend NPU (#9355) 
Co-authored-by: Even Zhou <even.y.zhou@outlook.com>
 2025-08-28 16:06:24 -07:00
zixuanzhang226
dc20c22f76 feat: add tuned fused moe config for GLM-4.5-Air-FP8 tp = 4 on B200 (#9770) 2025-08-28 16:00:28 -07:00
Lianmin Zheng
fce7ae33f8 [Sync] Update server_args.py (20250828) (#9745) 
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
 2025-08-28 10:33:00 -07:00
Qiaolin Yu
4a4772ae03 Support speculative decoding in hybrid attention backend (#9573) 2025-08-28 01:11:42 -07:00
yhyang201
c377923304 [feat] Reduce GPU memory overhead by using weakref (#9673) 2025-08-28 01:09:06 -07:00
zyksir
aee094e430 add support for nvidia/gpt-oss-120b-Eagle3 (#9739) 2025-08-28 00:20:20 -07:00
huangtingwei
55349e361d support mooncake store dp attention (#9684) 2025-08-28 12:31:31 +08:00
Lianmin Zheng
4aeba40d7b [Sync] Update mxfp4.py (20250827) (#9724) 
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
Co-authored-by: Shiyang Chen <shiyang@x.ai>
 2025-08-27 17:00:09 -07:00
Yineng Zhang
bc80dc4ce0 chore: bump v0.5.1.post3 (#9716) 2025-08-27 15:42:42 -07:00
Yineng Zhang
b962a296ed chore: upgrade sgl-kernel 0.3.7 (#9708) 2025-08-27 14:00:31 -07:00
PGFLMG
aa3eba8eb4 [sgl-kernel] misc: update deepgemm version for sgl-kernel (#9340) 
Co-authored-by: Yineng Zhang <me@zhyncs.com>
Co-authored-by: fzyzcjy <ch271828n@outlook.com>
 2025-08-27 12:01:30 -07:00
Xinyuan Tong
68a54e063e Sets default model name in request classes (#9683) 
Signed-off-by: Xinyuan Tong <xinyuantong.cs@gmail.com>
 2025-08-27 10:43:03 -07:00
ybyang
fd18995cf3 Fix get_ip when no external network (#9700) 2025-08-27 10:28:52 -07:00
yilian49
db0831e019 Quick fix for loading processor for supporting internvl3_5 series (#9676) 2025-08-27 09:05:27 -07:00
Lianmin Zheng
fd71b11b1d move is_sm90_supported/is_sm100_supported to python/sglang/srt/utils.py (#9679) 2025-08-27 03:34:29 -07:00
huangtingwei
ae7428a8a7 fix mooncake store mla zero copy meta (#9678) 2025-08-27 15:43:16 +08:00
Pablo Iyu Guerrero
a3aee7c377 fix: HiRadixCache: fix prefetch completion race (#9397) 2025-08-27 15:43:01 +08:00
ehuaa
8f7b1c31e8 Add A100 fused MoE kernel configs for Dpsk (#9677) 2025-08-26 20:49:48 -07:00
Xu Wenqing
b9683be653 Support DeepSeek-V3.1 tool call (#9446) 
Signed-off-by: 许文卿 <xwq391974@alibaba-inc.com>
Co-authored-by: Xinyuan Tong <xinyuantong.cs@gmail.com>
 2025-08-26 20:22:19 -07:00
Kevin Tuan
b21fdd5373 feat: (chat-template matching) enhance multimodal model detection with config.json (#9597) 2025-08-26 17:55:40 -07:00
hzh0425
c04c17edfa refactor(hicache): Introduce generic HiCacheStorageConfig for improved configuration management (#9555) 
Co-authored-by: Teng Ma <805522925@qq.com>
 2025-08-26 17:55:20 -07:00
Mick
16a6d21b95 chore: enhance bench_serving for vlms with a new dataset of configurable image count and resolution (#9583) 
Co-authored-by: yhyang201 <yhyang201@gmail.com>
 2025-08-26 17:42:54 -07:00
Stefan He
a530b3ffdc [RL] fix register the same ops multiple times (#9564) 2025-08-26 16:24:44 -07:00
Ke Bao
603b3446dc Fix FA3 swa spec verify topk>1 (#9658) 2025-08-26 15:03:14 -07:00
cicirori
b6c14ec0b4 add response_format support for completion API (#9665) 2025-08-26 15:01:29 -07:00
Zhiqiang Xie
43de1d7304 HiCache Storage fix host memory leak (#9648) 2025-08-26 10:49:40 -07:00
hzh0425
79ce3688bb BugFix(hicache): Fix host indices out of bound error (#9637) 
Co-authored-by: Zhiqiang Xie <xiezhq@stanford.edu>
 2025-08-26 10:42:23 -07:00
Xiaotong Jiang
0936c766ed Fix kimi k2 function calling format (#9606) 2025-08-26 00:50:59 -07:00
GavinZhu-GMI
0ef583b7de fix: allow user to specify function as role (#9635) 2025-08-26 00:47:20 -07:00
Liu Shaohui
f7881a27f9 Add reasoning_effort param in TiktokenTokenizer.apply_chat_template (#9630) 
Co-authored-by: Shaohui Liu <liushaohui3@xiaomi.com>
Co-authored-by: Xinyuan Tong <115166877+JustinTong0323@users.noreply.github.com>
 2025-08-26 00:44:20 -07:00
ZhengdQin
f92b729d52 [new feat] ascend backend support fia fusion kernel (#8328) 
Co-authored-by: Even Zhou <even.y.zhou@outlook.com>
 2025-08-25 23:13:08 -07:00
Liangsheng Yin
0ff7241995 Improve bench_one_batch_server script (#9608) 
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
 2025-08-26 10:38:37 +08:00
ykwd
80dc76e11a [Fix] HiCache Bugfix & Mooncake Error Handling Enhance (#8901) 
Co-authored-by: Zhiqiang Xie <xiezhq@stanford.edu>
 2025-08-25 19:05:10 -07:00
Jonas
a0a77d937b Fix Harmony reasoning parser for and auto-separation for gpt-oss models (#9190) 
Co-authored-by: Chang Su <chang.s.su@oracle.com>
Co-authored-by: Chayenne <zhaochen20@outlook.com>
Co-authored-by: zhaochenyang20 <zhaochenyang20@gmail.com>
Co-authored-by: minleminzui <2969413251@qq.com>
Co-authored-by: maocheng23 <maocheng@berkeley.edu>
Co-authored-by: Xinyuan Tong <xinyuantong.cs@gmail.com>
 2025-08-25 15:26:26 -07:00
Binyao Jiang
24a8cee66d Fix GLM45v launch server cuda torch compile bug (#9554) 2025-08-25 13:46:28 -07:00
Binyao Jiang
3affa9dcc3 Fix GLM45 tool call multi-turn bug (#9500) 2025-08-25 13:46:13 -07:00
Sundara Raman Ramachandran
ea0696b924 [Performance] Batch Send from Tokenizer Manager. (#9436) 2025-08-26 01:43:54 +08:00
Yineng Zhang
e3e97a120b chore: bump v0.5.1.post2 (#9592) 2025-08-25 03:45:09 -07:00
Yineng Zhang
051068673c chore: update config (#9591) 2025-08-25 03:41:09 -07:00
fzyzcjy
9dcdf5da03 Tiny fix wrong comments (#9589) 2025-08-25 03:08:10 -07:00
Yineng Zhang
ebd9dbe71b fix: revert #8593 (#9581) 2025-08-25 01:29:06 -07:00
Yineng Zhang
938e986e15 chore: upgrade flashinfer 0.2.14.post1 (#9578) 2025-08-25 00:12:17 -07:00
Yuhao Zhou
17d5eda887 bugfix for undefined logging functions in HarmonyBrowserTool & HarmonyPythonTool (#9229) 2025-08-25 00:10:35 -07:00
fzyzcjy
71a7f1d86f Offload tensors by sharding on GPU (#9536) 2025-08-25 00:02:49 -07:00
fzyzcjy
433266c125 Reintroduce memory usage fix (#9535) 2025-08-25 00:02:31 -07:00
Qi Yuhang
fda4792620 Update CUTLASS 4.2 & Enable K-Major Scale Factor for SM90 FP8 Blockwise Group GEMM (#9559) 2025-08-24 23:24:43 -07:00
miter
a0b22f2f17 remove redundant rank0_log function. (#9560) 
Co-authored-by: linhuang <linhuang@ruijie.com.cn>
 2025-08-24 23:17:55 -07:00
SCDESPERTATE
b5c6529e17 [PD] Improve disaggregation metrics output: update the metrics to keep reflecting real stats (#7317) 2025-08-24 23:16:43 -07:00
Beichen Ma
dd6ec02965 Add target module validation for init adapters (#9429) 2025-08-24 20:24:50 -07:00