Commits · a98496834bb5031208c674e639cc34f85d2b0617 · zhaoyu6 / sglang · GitLab

23 Oct, 2025 3 commits
- Feature/nano v2 offline modelopt fp8 and nvfp4 (#12018) · a9849683
  Netanel Haber authored Oct 23, 2025
```
Signed-off-by: Netanel Haber <58652339+netanel-haber@users.noreply.github.com>
```
  a9849683
- Revert "Support nvidia/NVIDIA-Nemotron-Nano-9B-v2-FP8/NVFP4" (#12015) · 6c18addb
  Liangsheng Yin authored Oct 23, 2025
  
  6c18addb
- Support nvidia/NVIDIA-Nemotron-Nano-9B-v2-FP8/NVFP4 (#11866) · d6fee73d
  Netanel Haber authored Oct 23, 2025
  
  d6fee73d
22 Oct, 2025 5 commits
- [NVIDIA] Update to leverage flashinfer trtllm FP4 MOE throughput kernel (#11563) · eec9e471
  jiahanc authored Oct 22, 2025
```
Signed-off-by: jiahanc <173873397+jiahanc@users.noreply.github.com>
```
  eec9e471
- [6/n]decouple quantization implementation from vLLM dependency (#10750) · d7e834d6
  Hongbo Xu authored Oct 23, 2025
  
  d7e834d6
- Enable native ModelOpt quantization support (3/3) (#10154) · 80b2b320
  Zhiyu authored Oct 21, 2025
```
Signed-off-by: Zhiyu Cheng <zhiyuc@nvidia.com>
```
  80b2b320
- [lint] improve ruff check (#11922) · 9d61205d
  Liangsheng Yin authored Oct 22, 2025
```
Co-authored-by: Xiaoyu Zhang <35585791+BBuf@users.noreply.github.com>
```
  9d61205d
- fix: resolve flashinfer 0.4.1 import (#11940) · 70416001
  Yineng Zhang authored Oct 21, 2025
  
  70416001
21 Oct, 2025 3 commits
- 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
- piecewise cuda graph support qwen3-moe (#11845) · 8374a96e
  Xiaoyu Zhang authored Oct 21, 2025
  
  8374a96e
20 Oct, 2025 2 commits
- [9/N] MoE Refactor: cleanup dispatcher interfaces (#11847) · bfc3b3f7
  Cheng Wan authored Oct 20, 2025
  
  bfc3b3f7
- Fix triton_kernels import error on some hardwares (#11831) · a8ba3279
  fzyzcjy authored Oct 20, 2025
  
  a8ba3279
19 Oct, 2025 1 commit
- Change bf16 to fp8 for some gemms in attention for DeepSeek ckpt v2 (#11805) · 12eb02e9
  fzyzcjy authored Oct 19, 2025
  
  12eb02e9
18 Oct, 2025 3 commits
- Use cutlass fp4 gemm by default (#11813) · ebda73dc
  Qiaolin Yu authored Oct 18, 2025
  
  ebda73dc
- [Refactor] move `deep_gemm_wrapper` out of `quantization` (#11784) · 5b214b50
  Cheng Wan authored Oct 17, 2025
  
  5b214b50
- Super tiny fix CI (#11788) · dcb8f090
  fzyzcjy authored Oct 18, 2025
  
  dcb8f090
17 Oct, 2025 2 commits
- Support shared experts overlap in cutlass moe (#11611) · 505329ca
  fzyzcjy authored Oct 18, 2025
  
  505329ca
- [Lint] Add `python/sglang` to ruff F401 checks and remove unused imports in files (#11685) · 62797440
  Chang Su authored Oct 17, 2025
  
  62797440
15 Oct, 2025 1 commit
- [1/N]Support DeepSeek-R1 w4a8 normal deepep (#8247) · 825432fc
  Jinwu authored Oct 15, 2025
```
Co-authored-by: Hank Han <hanhan7630@outlook.com>
```
  825432fc
13 Oct, 2025 4 commits
- Tiny cleanup fp4 gemm calls (#11537) · 065ce815
  fzyzcjy authored Oct 14, 2025
  
  065ce815
- Move deep gemm related arguments to `sglang.srt.environ` (#11547) · acc2327b
  Liangsheng Yin authored Oct 14, 2025
  
  acc2327b
- Depreate `global_server_args_dict` (#11528) · 516738b0
  Liangsheng Yin authored Oct 13, 2025
  
  516738b0
- Revert "Deprecate `global_server_args_dict`" (#11520) · 1bdd0102
  Cheng Wan authored Oct 12, 2025
  
  1bdd0102
12 Oct, 2025 2 commits
- Deprecate `global_server_args_dict` (#11331) · 1083e7e3
  Liangsheng Yin authored Oct 13, 2025
  
  1083e7e3
- [chore][1/N] Avoid using default mutable parameters (#11478) · 43190bec
  Kai-Hsun Chen authored Oct 12, 2025
```
Signed-off-by: Kai-Hsun Chen <khchen@x.ai>
```
  43190bec
11 Oct, 2025 2 commits
- Fix enable_v2 in int8 quant (#11470) · bf3e7149
  fzyzcjy authored Oct 11, 2025
  
  bf3e7149
- Reland [1/2] Optimizations and refactors about quant kernel (#10312) · 21337b22
  fzyzcjy authored Oct 11, 2025
```
Co-authored-by: Yineng Zhang <me@zhyncs.com>
```
  21337b22
09 Oct, 2025 1 commit
- move more files under srt/utils (#11285) · 9b8ebb27
  Lianmin Zheng authored Oct 09, 2025
  
  9b8ebb27
08 Oct, 2025 1 commit
- [8/N] MoE Refactor: deprecate `EPMoE` (#11211) · 3c06b673
  Cheng Wan authored Oct 07, 2025
  
  3c06b673
07 Oct, 2025 1 commit
- [quantization] Properly ignore quantization for layers excluded in quant_config (#11205) · cd4b39a9
  Bowen Bao authored Oct 07, 2025
  
  cd4b39a9
06 Oct, 2025 2 commits
- Enable native ModelOpt quantization support (1/3) (#7149) · 155cbb51
  Zhiyu authored Oct 06, 2025
```
Signed-off-by: Zhiyu Cheng <zhiyuc@nvidia.com>
```
  155cbb51
- [quantization] Enable aiter mxfp4 fused_moe for Quark (#10048) · baee0860
  Bowen Bao authored Oct 05, 2025
```
Co-authored-by: HaiShaw <hixiao@gmail.com>
```
  baee0860
02 Oct, 2025 2 commits
- Support single batch overlap (#10422) · 5e786cca
  fzyzcjy authored Oct 02, 2025
  
  5e786cca
- Support dispatch low latency (#10263) · 0b9dfba7
  fzyzcjy authored Oct 02, 2025
```
Co-authored-by: Kaixi Hou <4001424+kaixih@users.noreply.github.com>
```
  0b9dfba7
30 Sep, 2025 1 commit
- [model] added support for w8a8int8 used by neuralmagic/Qwen2-0.5B-Ins… (#9642) · 8831c55c
  DevashishLal-CB authored Sep 29, 2025
  
  8831c55c
27 Sep, 2025 2 commits
- [Fix] RuntimeError: get_cfg Unsupported input_type:Float4_e2m1fn_x2 in using... · 8ebf72fe
  kk authored Sep 27, 2025
```
[Fix] RuntimeError: get_cfg Unsupported input_type:Float4_e2m1fn_x2 in using aiter-mxfp4-moe (#10981)
Co-authored-by: wunhuang <wunhuang@amd.com>
```
  8ebf72fe
- fix: fp8 quantization failure of qwen 2.5 VL 7B model (#10112) · 82605747
  Yueyang Pan authored Sep 27, 2025
```
Signed-off-by: PanJason <pyyjason@gmail.com>
```
  82605747
26 Sep, 2025 1 commit
- Revert "Refactor kv_cache_scheme handling for quantization (#10132)" (#10935) · 172bcf01
  Yineng Zhang authored Sep 25, 2025
  
  172bcf01
25 Sep, 2025 1 commit
- Refactor kv_cache_scheme handling for quantization (#10132) · cd4da1f1
  Mohammad Miadh Angkad authored Sep 26, 2025
  
  cd4da1f1