kvcache-ai/sglang
1
0
Fork 0
mirror of https://github.com/kvcache-ai/sglang.git synced 2026-07-08 08:17:41 +00:00
Code Issues Packages Projects Releases Wiki Activity
9,408 Commits 157 Branches 0 Tags
522e13b4d2c1de1cfb44ecbbca374ec8f312de52
Commit Graph

6077 Commits

Author SHA1 Message Date
Xiaoming Liu
522e13b4d2 fix: correct weight loading prefix mapping for Qwen3-VL (#18024) 
Co-authored-by: liuxiaoming <liuxiaoming@modelbest.cn>
Co-authored-by: Xinyuan Tong <115166877+JustinTong0323@users.noreply.github.com>
 2026-02-01 21:50:21 -08:00
RangerCD
a480ca7ead fix: zmq_to_tokenizer encoder transfer when host listens to 0.0.0.0 (#17929) 2026-02-02 13:27:27 +08:00
siyu
f1824a957b [EPD][refactor]: introduce BaseMMReceiver for gRPC transport integration (#17921) 2026-02-02 11:37:32 +08:00
Cheng Wan
ab8b99eb23 Refine logprob logic for request handling (#17986) 2026-02-01 19:11:52 -08:00
Simon (Jiyou) Li
8ed35df204 Add bootstrap_room validation to detect metadata corruption in PD disaggregation (#17430) 
Co-authored-by: 继优 <jiyou.ljy@alibaba-inc.com>
Co-authored-by: Shangming Cai <csmthu@gmail.com>
 2026-02-02 10:43:50 +08:00
Mick
c84cd4b5ff [diffusion] fix: fix missing component names for VAELoader (#18069) 2026-02-02 09:48:17 +08:00
Mick
977096ae03 [diffusion] cli: introduce generic attention backend configuration in ServerArgs (#18036) 2026-02-02 09:47:40 +08:00
Yuhao Yang
d11ccc0a0a fix: avoid double reduce in VLM dp attention (#17991) 2026-02-02 09:44:32 +08:00
Yuan Luo
9227d4f748 [Fix] Remove no use code in MiMo-V2-Flash (#18051) 
Co-authored-by: luoyuan.luo <luoyuan.luo@antgroup.com>
 2026-02-01 15:34:09 -08:00
Glen Liu
99dad105fd [TestFix] rewrite LoRA overlap loading tests (#18047) 2026-02-01 14:52:08 -08:00
Koushik Dutta
993ec178ef [BUGFIX]: using language-only should not reserve space for the vision encoder (#18011) 
Co-authored-by: root <root@ubuntu-nvidia.localdomain>
 2026-02-01 14:49:00 -08:00
Lianmin Zheng
1acae30806 [Auto Sync] Update test_deterministic.py (20260131) (#18034) 
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
Co-authored-by: Jiayi Yuan <34369239+jy-yuan@users.noreply.github.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
 2026-02-01 07:40:07 -08:00
Lianmin Zheng
fb609669ca [Auto Sync] Update elementwise.py (20260131) (#18033) 
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
 2026-02-01 07:39:37 -08:00
Yuan Luo
4ea4f2a20c [VLM] Optimize get_rope_index for GLM4v (#17420) 
Co-authored-by: luoyuan.luo <luoyuan.luo@antgroup.com>
 2026-02-01 18:59:15 +08:00
jiashaokun-1
0fe282543f [NPU] support the Enable return routed experts (#17025) 2026-02-01 18:31:39 +08:00
Estrella-xx
27bec34203 [NPU] disaggregation_decode_enable_fake_auto parameter adaptation (#17811) 
Co-authored-by: ronnie_zheng <zl19940307@163.com>
Co-authored-by: Even Zhou <even.y.zhou@outlook.com>
 2026-02-01 18:14:26 +08:00
Ke Bao
d9050b4a9c Reset evict swa status when retract (#18059) 2026-02-01 17:17:37 +08:00
sunxxuns
47592a23c7 [CI] Fix AMD CI by inlining dummy_grok config (#18044) 
Co-authored-by: root <root@mi300x8-005.atl1.do.cpe.ice.amd.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-02-01 00:20:57 -08:00
yefei12
855dd0546c feat: Add Ling Flash v2.0 support for Eagle3 (#15119) 
Co-authored-by: chenyefei.cyf <chenyefei.cyf@U-9V5T77LW-2356.local>
Co-authored-by: GeLee-Q <865038696@qq.com>
Co-authored-by: Gao016 <yngao016@163.com>
Co-authored-by: Shenggui Li <somerlee.9@gmail.com>
Co-authored-by: Yineng Zhang <me@zhyncs.com>
 2026-01-31 23:57:45 -08:00
lukec
3ca29dffc7 support qwen3-next eagle3 (#14607) 2026-01-31 23:45:23 -08:00
Praneth Paruchuri
9bb1260558 [Feature] Support file:// URL format for multimodal inputs (#14490) 
Co-authored-by: Yuhao Yang <47235274+yhyang201@users.noreply.github.com>
 2026-01-31 23:44:44 -08:00
Roger Young
486c7de39f Optimizing all_reduce in RMSNormTP in minimax_m2 (#16483) 2026-01-31 23:39:37 -08:00
Kangyan-Zhou
9c168fcac7 Fix Diffusion Request Validation to allow missing input artifacts if the input only contains text (#16610) 2026-01-31 23:38:40 -08:00
tc-mb
4d28cda007 [model] Support MiniCPM-V 4.5 (#9610) 
Signed-off-by: tc-mb <caitianchi@modelbest.cn>
Co-authored-by: Xinyuan Tong <115166877+JustinTong0323@users.noreply.github.com>
 2026-01-31 23:37:36 -08:00
linhaifeng
2c036f1eb1 [Bugfix] fix the display error (inconsistent context) (#17699) 
Signed-off-by: linhaifeng <1371675203@qq.com>
 2026-01-31 23:35:11 -08:00
Ke Bao
d396650bd2 Fix swa kv cache memory allocation (#18039) 2026-02-01 14:26:51 +08:00
Minglei Zhu
38d275a9fd [BugFix] fix gpt-oss accuracy issue when enabling piecewise cuda graph (#18013) 2026-02-01 14:26:26 +08:00
Yinghai Lu
11892599f1 [metric] Optional extra metric labels (#18049) 2026-02-01 14:25:59 +08:00
Baizhou Zhang
c7d53fa26a Set torch url index in pyproject.toml (#16802) 2026-02-01 13:23:52 +08:00
khalilzhk
429ef988bc [BugFix] Fix draft model specified config file (#17815) 2026-01-31 20:45:36 -08:00
Kaixi
2b2515423a Skipped warning on sm100 (#18000) 2026-01-31 20:21:03 -08:00
Kangyan-Zhou
d443d2d2ae Improve error output in tnightly tets (#18053) 2026-01-31 19:26:19 -08:00
Yingchun Lai
0f2df9370a feat: validate ib devices in server args (#17598) 
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
Co-authored-by: Kangyan Zhou <zky314343421@gmail.com>
 2026-01-31 17:50:42 -08:00
b8zhong
398d13a189 [Perf] Add Flashinfer DeepGEMM SM90 for SwapAB Optimization (#15514) 
Co-authored-by: Brayden Zhong <b8zhong@users.noreply.github.com>
 2026-02-01 08:56:23 +08:00
Chongchong Tian
9951a1ae07 Fix: Remove duplicate assignment for use_w4afp8 (#17858) 2026-01-31 16:04:08 -08:00
Yi Zhong
c2ab3713e9 [Performance] Optimize Mllama LayerNorm -> Upd (#9725) 2026-01-31 16:02:57 -08:00
Hao Jin
6aaea09b3d Update python/sglang/README.md (#18045) 
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
 2026-01-31 13:20:41 -08:00
Zaili Wang
97593c9f41 [CPU] toml file update (#17861) 2026-01-31 13:16:06 -08:00
Mohammad Miadh Angkad
9ac4dcada4 [Tiny] Fix grammar in shared experts fusion log messages (#18043) 2026-01-31 13:14:25 -08:00
b8zhong
ef134d407d [Fix] Revert back to using CUTLASS mm_fp4 backend (#17369) 2026-01-31 23:01:29 +08:00
Mick
1a006c2a0d [diffusion] refactor: split component_loader into component-wise files (#17820) 2026-01-31 20:22:31 +08:00
Lianmin Zheng
7412ceb4eb [Auto Sync] Update linear.py to assert shapes (20260130) (#17966) 
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
Co-authored-by: Byron Hsu <byronhsu1230@gmail.com>
 2026-01-31 01:01:55 -08:00
Lianmin Zheng
0e184609d3 Add launch_command assignment in crash dump (#17967) 
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
Co-authored-by: Archit Patke <apatke@x.ai>
 2026-01-31 01:00:40 -08:00
b8zhong
22498e10c0 [Fix] Triton TP MoE Dpsk V3/Qwen3 Coder with SwapAB (#17965) 2026-01-31 15:56:26 +08:00
Zheng Wengang
a4df95c15f [EPD][Perf] parallelize ZMQ send for encode server (#16487) 
Co-authored-by: siyu <liusy58@linux.alibaba.com>
 2026-01-31 14:30:11 +08:00
jeff
04efd03dbf Fix OOM in DeepSeek weight loading by deferring dict(weights) materialization (#17744) 2026-01-31 13:59:00 +08:00
Hudson Xing
c72bf50706 add reasoning_tokens usage test for tool call (#18022) 2026-01-30 21:09:23 -08:00
Mohammad Miadh Angkad
d0d9cecd1b Fix cuBLAS >=12.9 detection for cu12/cu13 package naming (#17766) 2026-01-31 12:01:52 +08:00
Xiaoyu Zhang
22aad4e2c4 [Diffusion] Fix FLUX.1-schnell time embedding argument mismatch (#17988) 2026-01-31 11:47:27 +08:00
Bi Xue
5d00150e99 [sglang] fix mm token padded value overlap with text token id (#17781) 2026-01-30 17:09:13 -08:00