Commits · 251235c2299bff51cb3b3691ed0ec59aa6d15d23 · change / sglang

"server/text_generation_server/layers/marlin/gptq.py" did not exist on "8642250602bf9d0cf0fd7312f3e643458f3b3e09"

25 Oct, 2025 1 commit
- 适配v0.5.4 · 251235c2
  maxiao1 authored Oct 25, 2025
  
  251235c2
24 Oct, 2025 2 commits
- chore: bump SGLang version to 0.5.4 (#12027) · 1053e1be
  sglang-bot authored Oct 24, 2025
```
Co-authored-by: sglang-bot <sglang-bot@users.noreply.github.com>
```
  1053e1be
- Fixed aarch64 flash-mla (#12009) · 9a71500c
  nvjullin authored Oct 24, 2025
  
  9a71500c
23 Oct, 2025 30 commits
- [router] Add builder pattern for RouterConfig with zero duplication (#12030) · 6d6e24bc
  Simo Lin authored Oct 23, 2025
  
  6d6e24bc
- Update Github action title for kernel build (#12029) · 2c057fbf
  Kangyan-Zhou authored Oct 23, 2025
  
  2c057fbf
- Fix mamba radix cache eviction logic in `alloc_req_slots` (#11616) · dbd9435d
  Roger Young authored Oct 24, 2025
```
Signed-off-by: rogeryoungh <rogeryoungh@foxmail.com>
```
  dbd9435d
- Revert "[ROCm] Remove vLLM rope dependency & use AITER impl" (#12028) · 8ae9d4bb
  b8zhong authored Oct 23, 2025
  
  8ae9d4bb
- Log iteration # for prefill and decode (#9366) · 1c304aa9
  Nicolas Castet authored Oct 23, 2025
  
  1c304aa9
- model: support deepseek-ocr (#11891) · 770529a7
  Mick authored Oct 24, 2025
```
Co-authored-by: yhyang201 <47235274+yhyang201@users.noreply.github.com>
Co-authored-by: yhyang201 <yhyang201@gmail.com>
Co-authored-by: Shi Shuai <126407087+shuaills@users.noreply.github.com>
Co-authored-by: Xinyuan Tong <xinyuantong.cs@gmail.com>
```
  770529a7
- Add AWQ quantization support for NPU. (#10158) · 39c237f0
  ErvinXie authored Oct 24, 2025
```
Co-authored-by: Alisehen <814073252@qq.com>
Co-authored-by: Yaochen Han <48639761+Alisehen@users.noreply.github.com>
Co-authored-by: Zhengda Qin <zhengdqin@gmail.com>
```
  39c237f0
- [router][CI] Clean up imports and prints statements in sgl-router/py_test (#12024) · 28b8a406
  Chang Su authored Oct 23, 2025
  
  28b8a406
- ci: fix night-ci with push retry mechanism (#11765) · 8bd26dd4
  Mick authored Oct 24, 2025
  
  8bd26dd4
- [Auto Sync] Update test_deterministic_utils.py (20251023) (#12022) · ab07cd3e
  Lianmin Zheng authored Oct 23, 2025
```
Co-authored-by: Stefan He <hebiaobuaa@gmail.com>
```
  ab07cd3e
- 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
- [router] change ci names and update log level in ci (#12021) · a4b637d8
  Simo Lin authored Oct 23, 2025
  
  a4b637d8
- [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
- [Fix] memory leak by overlap + retract (#11981) · b0b4f716
  cctry authored Oct 23, 2025
```
Co-authored-by: Liangsheng Yin <lsyincs@gmail.com>
```
  b0b4f716
- Revert "Support nvidia/NVIDIA-Nemotron-Nano-9B-v2-FP8/NVFP4" (#12015) · 6c18addb
  Liangsheng Yin authored Oct 23, 2025
  
  6c18addb
- Move memory runtime checker to mixin class (#12014) · 32852fe9
  Liangsheng Yin authored Oct 23, 2025
  
  32852fe9
- [Router] Consolidate ConnectionMode enum to core module (#11937) · 53c2934d
  Arthur Cheng authored Oct 23, 2025
  
  53c2934d
- [router] Add comprehensive E2E tests for Response API (#11988) · e321c971
  Keyang Ru authored Oct 23, 2025
  
  e321c971
- Support nvidia/NVIDIA-Nemotron-Nano-9B-v2-FP8/NVFP4 (#11866) · d6fee73d
  Netanel Haber authored Oct 23, 2025
  
  d6fee73d
- Support overlap-spec-v2 with trtllm_mla attention backend (#11821) · 36a4cad7
  Qiaolin Yu authored Oct 23, 2025
  
  36a4cad7
- aiter update to v0.1.6.post1 (#12004) · 65d376b4
  HAI authored Oct 22, 2025
  
  65d376b4
- Fix incorrect KV indices creation when page_size=32 in TRTLLM MLA backend (#11985) · c23eda85
  yinghui authored Oct 22, 2025
  
  c23eda85
- Allow to disable batch decoding. (#11944) · 138ff231
  Jue WANG authored Oct 22, 2025
  
  138ff231
- [CPU] Optimize FP16 decode_attention_cpu (#10652) · 13fb8b54
  blzheng authored Oct 23, 2025
  
  13fb8b54
- fix(deepep): resolve benchmark failure on 4×IB-card setup by aligning tuning... · 81fd2b0e
  Zhengyi Lai authored Oct 23, 2025
```
fix(deepep): resolve benchmark failure on 4×IB-card setup by aligning tuning config with DeepEP commit bdd119f8 (#11965)
```
  81fd2b0e
- [CPU] misc updates (#11906) · 007b849b
  Zaili Wang authored Oct 23, 2025
  
  007b849b
- Bump grace blackwell DeepEP version (#11990) · 8612811d
  fzyzcjy authored Oct 23, 2025
  
  8612811d
- [NVIDIA] Build CUDA 13 (#11299) · e7aa4664
  Johnny authored Oct 22, 2025
```
Co-authored-by: ishandhanani <ishandhanani@gmail.com>
Co-authored-by: Baizhou Zhang <sobereddiezhang@gmail.com>
```
  e7aa4664
- [ROCm] Remove vLLM rope dependency & use AITER impl (#11322) · 4d4feccb
  b8zhong authored Oct 22, 2025
  
  4d4feccb
- [AMD] Support a new flag to disable quant on parallelLinear layer if required (#11811) · 99c92ff2
  jacky.cheng authored Oct 23, 2025
  
  99c92ff2
22 Oct, 2025 7 commits
- [grpc] Support gRPC standard health check (#11955) · 6ade6a02
  Chang Su authored Oct 22, 2025
  
  6ade6a02
- [Doc] Update deterministic inference flag in server_arguments.md (#11978) · 983ef22c
  Baizhou Zhang authored Oct 22, 2025
```
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
```
  983ef22c
- Implement BGE-M3 Sparse Embeddings in SGLang (#10869) · 164302c7
  Christian Bahls authored Oct 22, 2025
```
Co-authored-by: Christian Bahls <christian.bahls@planet-ai.de>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
```
  164302c7
- [router] create worker removal step and clean up worker manager (#11921) · 5dccf697
  Simo Lin authored Oct 22, 2025
  
  5dccf697
- [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
- Revert "Recapture cuda graph after model weight update to resolve IMA error " (#11980) · 6d535b71
  Lianmin Zheng authored Oct 22, 2025
  
  6d535b71
- [BUG] AttributeError: 'DeepEPMoE' object has no attribute 'use_w4a… (#11977) · fdcb1d13
  yuho authored Oct 23, 2025
  
  fdcb1d13