Commits · f35f120d700fe425296f790d6e5669af621244b9 · zhaoyu6 / sglang

13 Oct, 2025 2 commits
- fix: fix video input for qwen3-vl (#11442) · f35f120d
  Mick authored Oct 14, 2025
  
  f35f120d
- [Reland] perf: optimize qwen-vl with symm mem allreduce (#11457) · 0b6f535f
  Yuan Luo authored Oct 13, 2025
```
Co-authored-by: luoyuan.luo <luoyuan.luo@antgroup.com>
```
  0b6f535f
10 Oct, 2025 4 commits
- Revert "fix: fix video input for qwen3-vl" (#11437) · b4408e60
  Lianmin Zheng authored Oct 10, 2025
  
  b4408e60
- Revert "perf: optimize qwen-vl with symm mem allreduce" (#11436) · 52fcbbb8
  Cheng Wan authored Oct 10, 2025
  
  52fcbbb8
- perf: optimize qwen-vl with symm mem allreduce (#11381) · 3b9d97f3
  Yuan Luo authored Oct 10, 2025
```
Co-authored-by: luoyuan.luo <luoyuan.luo@antgroup.com>
```
  3b9d97f3
- fix: fix video input for qwen3-vl (#11361) · a1a20b4c
  Mick authored Oct 10, 2025
  
  a1a20b4c
01 Oct, 2025 1 commit
- Quick Fix: fix Qwen3-VL launch failure caused by MRotaryEmbedding arg (#10985) · 61305291
  yhyang201 authored Oct 01, 2025
  
  61305291
28 Sep, 2025 2 commits
- Fix FusedSetKVBufferArg in RotaryEmbedding (#11003) · 07440f5f
  Lianmin Zheng authored Sep 28, 2025
  
  07440f5f
- Fix CI failure of TypeError: RotaryEmbedding.forward_cpu() got an unexpected... · 66face35
  YanbingJiang authored Sep 28, 2025
```
Fix CI failure of TypeError: RotaryEmbedding.forward_cpu() got an unexpected keyword argument 'fused_set_kv_buffer_arg' (#11009)
```
  66face35
23 Sep, 2025 3 commits

model: support qwen3-vl series (#10323) · 4f564b9e

Zheng Li authored Sep 24, 2025


Co-authored-by: ocss884 <ocss.lin@gmail.com>
Co-authored-by: cao1zhg <653506626@qq.com>
Co-authored-by: yhyang201 <yhyang201@gmail.com>
Co-authored-by: yhyang201 <47235274+yhyang201@users.noreply.github.com>
Co-authored-by: 瑀澈 <yuche.lz@alibaba-inc.com>
Co-authored-by: Mick <mickjagger19@icloud.com>
Co-authored-by: Yineng Zhang <me@zhyncs.com>

4f564b9e

[Ascend] optimize Qwen-vl on Ascend (#10556) · 095093ee
ronnie_zheng authored Sep 23, 2025
```
Co-authored-by: wangqihui01 <wangqh10@163.com>
```
095093ee
[Feature] Add MLAProcess for DeepSeek MLA on NPU (#10130) · d27a6f70
Even Zhou authored Sep 23, 2025

d27a6f70

03 Sep, 2025 1 commit
- Remove mrope position sync (#9460) · 4ed9053e
  timmy-feng authored Sep 03, 2025
```
Co-authored-by: Nathan Wang <nathan.r.wang@gmail.com>
```
  4ed9053e
31 Aug, 2025 1 commit
- [feat]Ascend NPU Gemma-3-12b and Gemma-3-27b support (#8909) · ba861293
  VDV1985 authored Aug 31, 2025
  
  ba861293
22 Aug, 2025 1 commit
- torch.compile() mrope (#9487) · 61a0e600
  timmy-feng authored Aug 22, 2025
  
  61a0e600
12 Aug, 2025 1 commit
- Fuse writing KV buffer into rope kernel (part 2: srt) (#9014) · c9ee7385
  Jiaqi Gu authored Aug 12, 2025
```
Co-authored-by: fzyzcjy <5236035+fzyzcjy@users.noreply.github.com>
```
  c9ee7385
09 Aug, 2025 2 commits

[Feature] Optimize DeepSeek's DeepEP on Ascend NPU (#8355) · 137e75da
Even Zhou authored Aug 09, 2025
```
Co-authored-by: ronnie_zheng <zl19940307@163.com>
Co-authored-by: Hexq0210 <hexq0809521@gmail.com>
```
137e75da

Support glm4.1v and glm4.5v (#8798) · f29aba8c

Binyao Jiang authored Aug 09, 2025


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>

f29aba8c

07 Aug, 2025 1 commit
- [Feat] QWen-1M context support[2/2]: Update block sparse attention backend (#5949) · b7cd7430
  PGFLMG authored Aug 07, 2025
  
  b7cd7430
03 Jul, 2025 1 commit

Ascend attention backend(PA&MLA) (#7722) · 1e0e5497

ronnie_zheng authored Jul 03, 2025


Co-authored-by: Maksim <makcum888e@mail.ru>
Co-authored-by: VDV1985 <vladdv85@mail.ru>

1e0e5497

26 Jun, 2025 1 commit
- Add Tencent HunYuanMoEV1 model support (#7549) · 2390a2bc
  Meng, Peng authored Jun 26, 2025
  
  2390a2bc
25 Jun, 2025 2 commits
- take aiter get_rope back (#7521) · 802815e4
  valarLip authored Jun 25, 2025
  
  802815e4
- npu fused op (#7386) · 506a2d59
  ll819214 authored Jun 25, 2025
```
Co-authored-by: Li Junwen <lijunwen13@hisilicon.com>
```
  506a2d59
18 Jun, 2025 1 commit

Update python API of activation, topk, norm and rope and remove vllm dependency (#6614) · 094c116f

YanbingJiang authored Jun 18, 2025


Co-authored-by: Wu, Chunyuan <chunyuan.wu@intel.com>
Co-authored-by: jianan-gu <jianan.gu@intel.com>
Co-authored-by: sdp <sdp@gnr799219.jf.intel.com>

094c116f

17 Jun, 2025 1 commit
- support qwen2 running on ascend npu device (#7022) · a39d9287
  Yijie Zhu authored Jun 18, 2025
```
Co-authored-by: 刁莹煜 <diaoyingyu1@hisilicon.com>
```
  a39d9287
04 Jun, 2025 1 commit
- [fix] recover auto-dispatch for rmsnorm and rope (#6745) · 180ff5ee
  JieXin Liang authored Jun 04, 2025
  
  180ff5ee
12 May, 2025 2 commits
- Revert "fix some typos" (#6244) · e8e18dcd
  Lianmin Zheng authored May 12, 2025
  
  e8e18dcd
- fix some typos (#6209) · d738ab52
  applesaucethebun authored May 12, 2025
```
Co-authored-by: Brayden Zhong <b8zhong@uwaterloo.ca>
```
  d738ab52
27 Apr, 2025 3 commits
- Revert "Revert "fix: import vllm_rotary_embedding error when head_size not in... · 6e313c1b
  Lianmin Zheng authored Apr 27, 2025
```
Revert "Revert "fix: import vllm_rotary_embedding error when head_size not in 64, 128, 256, 512"" (#5777)
```
  6e313c1b
- Revert "fix: import vllm_rotary_embedding error when head_size not in 64, 128, 256, 512" (#5772) · 8ba31330
  Lianmin Zheng authored Apr 26, 2025
  
  8ba31330
- fix: import vllm_rotary_embedding error when head_size not in 64, 128, 256, 512 (#5733) · 63c13a2c
  Kyungmin Lee authored Apr 27, 2025
  
  63c13a2c
26 Apr, 2025 1 commit

fix: fix one more bug from merging mm_inputs (#5718) · feda9b11

Mick authored Apr 26, 2025


Co-authored-by: Xinyuan Tong <justinning0323@outlook.com>
Co-authored-by: XinyuanTong <115166877+JustinTong0323@users.noreply.github.com>

feda9b11

24 Apr, 2025 1 commit
- vlm: enable radix cache for qwen-vl models (#5349) · c998d04b
  Mick authored Apr 24, 2025
```
Co-authored-by: Xinyuan Tong <justinning0323@outlook.com>
```
  c998d04b
22 Apr, 2025 1 commit
- Remove extra copy in deepseek forward absorb (#5578) · 11b23ae9
  Ke Bao authored Apr 22, 2025
```
Co-authored-by: saienduri <saimanas.enduri@amd.com>
```
  11b23ae9
21 Apr, 2025 1 commit
- [misc] remove is_cuda_available (#5319) · 97cb762b
  JieXin Liang authored Apr 21, 2025
  
  97cb762b
16 Apr, 2025 1 commit
- Clean up imports (#5467) · 177320a5
  Lianmin Zheng authored Apr 16, 2025
  
  177320a5
15 Apr, 2025 1 commit
- Tiny fix DeepseekScalingRotaryEmbedding always use forward_native (#5406) · 15e91d72
  fzyzcjy authored Apr 15, 2025
  
  15e91d72
14 Apr, 2025 1 commit
- Apply deepseek cuda rope (#5385) · 5e0a9b09
  Ke Bao authored Apr 15, 2025
```
Co-authored-by: Yineng Zhang <me@zhyncs.com>
```
  5e0a9b09
07 Apr, 2025 1 commit

Add Llama4 support (#5092) · f04c80dc

Chang Su authored Apr 07, 2025


Co-authored-by: Cheng Wan <cwan39@gatech.edu>
Co-authored-by: fzyzcjy <ch271828n@outlook.com>
Co-authored-by: ispobock <ispobaoke@163.com>

f04c80dc

01 Apr, 2025 1 commit
- Revert PR 4764 & 4813 related to R1 RoPE (#4959) · 87fafa01
  Yuhong Guo authored Apr 01, 2025
  
  87fafa01