Commits · 4b046a72d3598cad6beee92f19db6f789af919ac · zhaoyu6 / sglang

24 Oct, 2025 3 commits
- docs(server-arguments): add allowed options for each argument (#11560) · 4b046a72
  Jonah Bernard authored Oct 24, 2025
  
  4b046a72
- Use flashinfer_trtllm moe runner backend to gain around 10% perf on b200 fp8 dpsk (#11816) · f80371ff
  b8zhong authored Oct 23, 2025
  
  f80371ff
- Enable Llama 4 + TRTLLM MHA (#12003) · 47e12e08
  b8zhong authored Oct 23, 2025
  
  47e12e08
23 Oct, 2025 2 commits

[Feature] Support loading weights from ckpt engine worker (#11755) · 96a5e4dd

Teng Ma authored Oct 24, 2025


Signed-off-by: Yang Kaiyong <yangkaiyong.yky@antgroup.com>
Signed-off-by: Cruz Zhao <CruzZhao@linux.alibaba.com>
Signed-off-by: Xuchun Shang <xuchun.shang@gmail.com>
Co-authored-by: Yang Kaiyong <yangkaiyong.yky@antgroup.com>
Co-authored-by: Cruz Zhao <CruzZhao@linux.alibaba.com>
Co-authored-by: Xuchun Shang <xuchun.shang@gmail.com>
Co-authored-by: Shangming Cai <csmthu@gmail.com>

96a5e4dd

Allow to disable batch decoding. (#11944) · 138ff231
Jue WANG authored Oct 22, 2025

138ff231

22 Oct, 2025 2 commits
- [2/N] Added the core structure of elastic EP and the eplb algorithm with faulty rank (#10606) · 904655c5
  Hank Han authored Oct 22, 2025
```
Co-authored-by: Xun Sun <UNIDY2002@outlook.com>
Co-authored-by: Shangming Cai <csmthu@gmail.com>
```
  904655c5
- Enable native ModelOpt quantization support (3/3) (#10154) · 80b2b320
  Zhiyu authored Oct 21, 2025
```
Signed-off-by: Zhiyu Cheng <zhiyuc@nvidia.com>
```
  80b2b320
21 Oct, 2025 4 commits
- Rename flashmla kernel options of nsa backend for better readability (#11876) · ef4a8097
  Baizhou Zhang authored Oct 21, 2025
  
  ef4a8097
- init support for KTransformers Heterogeneous Computing (#11487) · 7e6191c0
  Atream authored Oct 21, 2025
```
Co-authored-by: Jianwei Dong <1913953267@qq.com>
```
  7e6191c0
- Init attention backend for Intel XPU (#10656) · b113c72e
  Meng, Hengyu authored Oct 21, 2025
```
Co-authored-by: guangyey <guangye.yu@intel.com>
Co-authored-by: DiweiSun <105627594+DiweiSun@users.noreply.github.com>
```
  b113c72e
- [Auto Sync] Update scheduler.py, server_args.py (20251020) (#11875) · 43ad0590
  Lianmin Zheng authored Oct 20, 2025
```
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
Co-authored-by: Kan Wu <wukanustc@gmail.com>
```
  43ad0590
20 Oct, 2025 4 commits
- fix(server_args): handle tokenizer init conflicts (#11776) · 296f6892
  ishandhanani authored Oct 20, 2025
  
  296f6892
- [Model] Add Olmo 3 model support (#11396) · d383e661
  Shane A authored Oct 19, 2025
  
  d383e661
- [NVIDIA] FA3/FA4 Fix (#11606) · 252dc4e1
  Johnny authored Oct 20, 2025
```
Co-authored-by: Baizhou Zhang <sobereddiezhang@gmail.com>
```
  252dc4e1
- [CI] Add CI test for DeepSeek V3.2 MTP (#11835) · cbb5fc2e
  Baizhou Zhang authored Oct 19, 2025
  
  cbb5fc2e
19 Oct, 2025 1 commit
- Deterministic Mode: Add 1-stage triton kernel for prefill (#11147) · 4fff1ec1
  Stefan He authored Oct 19, 2025
```
Co-authored-by: Minglei Zhu <mingleizhu1122@gmail.com>
Co-authored-by: Binyao Jiang <bijiang@linkedin.com>
```
  4fff1ec1
18 Oct, 2025 4 commits
- support server arg override KV cache to bf16 to avoid slow cases (#11749) · f9a7d9b3
  b8zhong authored Oct 18, 2025
  
  f9a7d9b3
- Fix install instructions and pyproject.tomls (#11781) · 67e34c56
  Lianmin Zheng authored Oct 18, 2025
  
  67e34c56
- Eager Compiler for Torch Compile (#11803) · 1d726528
  Yuwei An authored Oct 18, 2025
```
Signed-off-by: Oasis-Git <ayw.sirius19@gmail.com>
```
  1d726528
- set default attention backend for deterministic inference (#11801) · f4488e9d
  Minglei Zhu authored Oct 18, 2025
  
  f4488e9d
17 Oct, 2025 2 commits
- [minor] sync code on python/sglang/test/test_deterministic.py and improve ci tests (#11777) · b9a54e09
  Lianmin Zheng authored Oct 17, 2025
```
Co-authored-by: Stefan He <hebiaobuaa@gmail.com>
Co-authored-by: Byron Hsu <byronhsu1230@gmail.com>
```
  b9a54e09
- Revert "Set csgmv as default lora backend. (#11488)" (#11735) · da681f35
  Yineng Zhang authored Oct 17, 2025
  
  da681f35
16 Oct, 2025 5 commits
- Revert "make radix cache deterministic" (#11728) · b0d1d717
  Baizhou Zhang authored Oct 16, 2025
  
  b0d1d717
- [Bugfix] Fix Qwen3/DSV3/DSV3.2 model support (#11510) · 3cceaa38
  Even Zhou authored Oct 16, 2025
  
  3cceaa38
- Set csgmv as default lora backend. (#11488) · b0d20cde
  Lifu Huang authored Oct 15, 2025
  
  b0d20cde
- [Mamba] Increase default mamba_full_memory_ratio to 0.9 (#11679) · 97d857c0
  Hanming Lu authored Oct 15, 2025
  
  97d857c0
- Sync code and test CI; rename some env vars (#11686) · cd7e1bd5
  Lianmin Zheng authored Oct 15, 2025
  
  cd7e1bd5
15 Oct, 2025 2 commits
- [1/N]Support DeepSeek-R1 w4a8 normal deepep (#8247) · 825432fc
  Jinwu authored Oct 15, 2025
```
Co-authored-by: Hank Han <hanhan7630@outlook.com>
```
  825432fc
- [1/N] Introduce Mooncake Backend and Mooncake EP to Support Elastic EP (#10423) · a40229f6
  Xun Sun authored Oct 15, 2025
```
Co-authored-by: Hank Han <hanhan7630@outlook.com>
Co-authored-by: Shangming Cai <csmthu@gmail.com>
```
  a40229f6
14 Oct, 2025 3 commits
- [Auto Sync] Update scheduler.py, server_args.py (20251014) (#11623) · 27d71045
  Lianmin Zheng authored Oct 14, 2025
```
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
Co-authored-by: Stefan He <hebiaobuaa@gmail.com>
```
  27d71045
- make radix cache deterministic (#10721) · dc965db0
  Alex Chi Z authored Oct 14, 2025
```
Signed-off-by: Alex Chi Z <iskyzh@gmail.com>
```
  dc965db0
- Implement LRU eviction policy for LoRA adapters (#11041) · 28f80b12
  Chenxi Li authored Oct 13, 2025
  
  28f80b12
13 Oct, 2025 7 commits
- [router][grpc] Add `serve_grpc` to `launch_server` and log id for HealthCheck (#11564) · 887c2b45
  Chang Su authored Oct 13, 2025
  
  887c2b45
- Fix DeepSeek-v3.2 default config (ValueError: not enough values to unpack... · c9cff2b9
  Trevor Morris authored Oct 13, 2025
```
Fix DeepSeek-v3.2 default config (ValueError: not enough values to unpack (expected 4, got 3)) (#11557)
```
  c9cff2b9
- Depreate `global_server_args_dict` (#11528) · 516738b0
  Liangsheng Yin authored Oct 13, 2025
  
  516738b0
- [Feature] Support mamba radix cache v0 (#11214) · a55cf530
  Yi Zhang authored Oct 13, 2025
```
Co-authored-by: hanming-lu <hanming@x.ai>
Co-authored-by: hzh0425 <hzh0425@apache.org>
Co-authored-by: thalahors <ericalcaide1@gmail.com>
```
  a55cf530
- Update DeepSeek-R1-FP4 default config on blackwell (#11512) · a2b3d9b9
  Qiaolin Yu authored Oct 12, 2025
  
  a2b3d9b9
- Improve dp attention port assignment scheme (#5889) · a20e7df8
  Yongtong Wu authored Oct 13, 2025
```
Co-authored-by: Cheng Wan <cwan@x.ai>
```
  a20e7df8
- Revert "Deprecate `global_server_args_dict`" (#11520) · 1bdd0102
  Cheng Wan authored Oct 12, 2025
  
  1bdd0102
12 Oct, 2025 1 commit
- Sync changes on io_struct.py and deterministic ops (#11498) · 2ac46e94
  Lianmin Zheng authored Oct 12, 2025
  
  2ac46e94