Commits · bf3352c5592357369f08d7acd2fe14225b582524 · zhaoyu6 / sglang

"test/vscode:/vscode.git/clone" did not exist on "8fefdd32c7c3e101cf4286643a6d8dbcc73751b7"

27 Jul, 2025 13 commits
- [hotfix] fix merge conflicts in FlashInferEPMoE (#8405) · 4d921f2b
  Cheng Wan authored Jul 27, 2025
  
  4d921f2b
- Support precomputed_embeddings for Llama 4 (#8156) · 44d600cd
  Kevin Xiang Li authored Jul 27, 2025
```
Signed-off-by: Xinyuan Tong <xinyuantong.cs@gmail.com>
Co-authored-by: Xiang (Kevin) Li <lik@nvidia.com>
Co-authored-by: Xinyuan Tong <115166877+JustinTong0323@users.noreply.github.com>
Co-authored-by: Xinyuan Tong <xinyuantong.cs@gmail.com>
```
  44d600cd
- Use FlashInfer FP4 gemm. (#8241) · 5c9c275b
  Elfie Guo authored Jul 27, 2025
  
  5c9c275b
- [2/N] MoE Refactor: Unify weight loader and quant methods (#8397) · bf0f448f
  Cheng Wan authored Jul 27, 2025
  
  bf0f448f
- fix: fix the missing metrics on non-rank0 nodes (#7720) · 36d6f0ba
  Yingchun Lai authored Jul 27, 2025
  
  36d6f0ba
- Add A800 fused MoE kernel tuning configs for Qwen3-Coder-480B-A35B-Instruct (#8351) · 2a1936de
  Li Hui authored Jul 27, 2025
  
  2a1936de
- fix: minor fix TransportProxyTensor under tp (#8382) · 0bcc195f
  Mick authored Jul 27, 2025
  
  0bcc195f
- [NVIDIA] Add Flashinfer MoE blockscale fp8 backend (#8036) · 85486b6f
  Kaixi Hou authored Jul 27, 2025
  
  85486b6f
- Minor tool for comparison of benchmark results (#7974) · 62222bd2
  fzyzcjy authored Jul 27, 2025
  
  62222bd2
- Tool to dump and compare internal activation tensors (#7976) · ed0fdbf3
  fzyzcjy authored Jul 27, 2025
  
  ed0fdbf3
- Urgent Fix: intern-s1 chat-template matching (#8403) · b602f423
  Xinyuan Tong authored Jul 27, 2025
```
Signed-off-by: Xinyuan Tong <justinning0323@outlook.com>
```
  b602f423
- HiCache, check before terminate prefetching (#8372) · 528bd1ed
  Zhiqiang Xie authored Jul 26, 2025
  
  528bd1ed
- Remove slot usage in code to be backward-compatible with python 3.9 (#8396) · 76154631
  Lifu Huang authored Jul 26, 2025
  
  76154631
26 Jul, 2025 8 commits
- Add perf tests for LoRA (#8314) · 5c705b1d
  Lifu Huang authored Jul 26, 2025
  
  5c705b1d
- model: support intern-s1 (#8350) · b7094a5e
  RunningLeon authored Jul 27, 2025
```
Signed-off-by: Xinyuan Tong <xinyuantong.cs@gmail.com>
Co-authored-by: zxy <zhou0493@e.ntu.edu.sg>
Co-authored-by: Xinyuan Tong <xinyuantong.cs@gmail.com>
Co-authored-by: Mick <mickjagger19@icloud.com>
Co-authored-by: Xinyuan Tong <115166877+JustinTong0323@users.noreply.github.com>
```
  b7094a5e
- Tiny assert EPLB is used together with expert parallel (#8381) · da0c0260
  fzyzcjy authored Jul 26, 2025
  
  da0c0260
- vlm: optimize tensor transport (#6003) · 3212c2ad
  Mick authored Jul 26, 2025
```
Co-authored-by: Xinyuan Tong <115166877+JustinTong0323@users.noreply.github.com>
```
  3212c2ad
- chore: improvements on mm_utils (#7737) · 53475674
  Mick authored Jul 26, 2025
  
  53475674
- Extract update_weights from RL Engine to SGLang to keep simplicity and fix torch reduce (#8267) · ce32bc2b
  Stefan He authored Jul 26, 2025
```
Co-authored-by: CuiBo 82354186+SuperCB@users.noreply.github.com
Co-authored-by: GeLee 865038696@qq.com
Co-authored-by: 杨睿 yangruipis@163.com
```
  ce32bc2b
- Save peak memory in logits processor (#8343) · e236d8fe
  Cheng Wan authored Jul 26, 2025
  
  e236d8fe
- chore: bump v0.4.9.post4 (#8305) · 2272c2a5
  Yineng Zhang authored Jul 25, 2025
  
  2272c2a5
25 Jul, 2025 14 commits
- Fix FP4 MoE accuracy from missing routed_scaling_factor (#8333) · 58c468f4
  Trevor Morris authored Jul 25, 2025
  
  58c468f4
- fix: kimi k2 xgrammar crash (#8367) · f8ca2368
  Yineng Zhang authored Jul 25, 2025
```
Co-authored-by: cicirori <32845984+cicirori@users.noreply.github.com>
Co-authored-by: gongwei-130 <56567052+gongwei-130@users.noreply.github.com>
```
  f8ca2368
- [Feat] Add reasoning parser for Qwen/Qwen3-235B-A22B-Thinking-2507 (#8363) · d8ee1564
  Chang Su authored Jul 25, 2025
  
  d8ee1564
- Clean up server_args, triton cache manager (#8332) · ed2e313e
  Lianmin Zheng authored Jul 25, 2025
  
  ed2e313e
- [Bugfix][Feat] Add XML-ish grammar in EBNFComposer and fix misc bugs in Qwen3 detector (#8357) · f8260f25
  Chang Su authored Jul 25, 2025
  
  f8260f25
- Add H20-3e fused MoE kernel tuning configs for Qwen3-Coder-480B-A35B-Instruct (#8344) · 12cb760a
  Xu Wenqing authored Jul 26, 2025
```
Signed-off-by: 许文卿 <xwq391974@alibaba-inc.com>
```
  12cb760a
- [P/D] Support ipv6 in P/D scenario (#7858) · 1b9cea5a
  Stepan Kargaltsev authored Jul 25, 2025
```
Co-authored-by: Shangming Cai <caishangming@linux.alibaba.com>
```
  1b9cea5a
- [torch.compile bug] avoid biased_grouped_topk_impl func repeatedly triggering... · 9045cc1e
  Xiaoyu Zhang authored Jul 25, 2025
```
[torch.compile bug] avoid biased_grouped_topk_impl func repeatedly triggering `torch.compile` in forward pass (#8353)
```
  9045cc1e
- [AMD] Add silu_and_mul, gelu_and_mul, gelu_tanh_and_mul, and gelu_quick... · af4b9bae
  Hubert Lu authored Jul 24, 2025
```
[AMD] Add silu_and_mul, gelu_and_mul, gelu_tanh_and_mul, and gelu_quick kernels for AMD GPUs (#7135)
Co-authored-by: yiakwy-xpu-ml-framework-team <961186938@qq.com>
Co-authored-by: HAI <hixiao@gmail.com>
```
  af4b9bae
- fix: Fix failed functional tests https://github.com/meta-llama/llama-stack-evals (#8266) · 7ad6b766
  Ying Wang authored Jul 24, 2025
  
  7ad6b766
- DP Enhancement (#8280) · c0fb25e9
  Cheng Wan authored Jul 24, 2025
  
  c0fb25e9
- [Feature] Integrate quick allreduce and select the best allreduce implementation (#6619) · 28d4d472
  li haoyang authored Jul 25, 2025
```
Signed-off-by: Haoyang Li <Haoyang.Li@amd.com>
Co-authored-by: ilmarkov <imarkov@redhat.com>
```
  28d4d472
- support idle batch for TBO (#8233) · f4674df6
  ZhichenJiang authored Jul 25, 2025
  
  f4674df6
- HiCache Storage TP Refinement (#8307) · 145482f4
  Zhiqiang Xie authored Jul 24, 2025
```
Co-authored-by: pansicheng <sicheng.pan.chn@gmail.com>
```
  145482f4
24 Jul, 2025 5 commits
- chore: upgrade flashinfer v0.2.9rc1 (#8301) · 8d1c5b94
  Swipe4057 authored Jul 25, 2025
```
Co-authored-by: Yineng Zhang <me@zhyncs.com>
```
  8d1c5b94
- [code style] Clean dead triton kernel code in fused_moe and useless vllm_ops import (#8310) · a167fd0b
  Xiaoyu Zhang authored Jul 24, 2025
  
  a167fd0b
- fix bug when eos_ids==0 (#8315) · bfb118c0
  Minho Ryu authored Jul 24, 2025
  
  bfb118c0
- [bug] fix pd completion protocol for batching support (#8317) · 5dd0f870
  Simo Lin authored Jul 23, 2025
  
  5dd0f870
- Pin the version of petit kernel to fix the APIs (#8235) · f7e102d5
  Haohui Mai authored Jul 23, 2025
  
  f7e102d5