Commits · 67fc595bb84670c46770f9cb062cae8b4a371f11 · change / sglang

"vscode:/vscode.git/clone" did not exist on "4b3507f0366d927a61fb2d21c6c3effd9889d508"

18 Feb, 2025 5 commits
- [Feature] Apply Cublas Grouped Gemm kernel (#3629) · 67fc595b
  Baizhou Zhang authored Feb 17, 2025
  
  67fc595b
- fix #3654 · 07ab4d4a
  Yineng Zhang authored Feb 18, 2025
  
  07ab4d4a
- Update amd docker image. (#3654) · 522e18ea
  saienduri authored Feb 17, 2025
  
  522e18ea
- Docs: Deploy multi-node inference (LWS method) using sglang in a K8s cluster (#3624) · c51dc2cc
  ybyang authored Feb 18, 2025
  
  c51dc2cc
- [ROCm] Optimal MOE Tuning for AMD Radeon Graphics (#3567) · ddf39d3f
  yigex authored Feb 18, 2025
  
  ddf39d3f
17 Feb, 2025 13 commits
- [ROCm] Add additional block quant GEMM tuning configs for AMD GPUs. (#3616) · 2eab1132
  Wen-Heng (Jack) Chung authored Feb 17, 2025
```
Co-authored-by: HAI <hixiao@gmail.com>
```
  2eab1132
- use transformers 4.48.3 (#3650) · 058d199d
  Yineng Zhang authored Feb 18, 2025
  
  058d199d
- chore: bump v0.4.3.post2 (#3645) · a5375adc
  Yineng Zhang authored Feb 18, 2025
```
Co-authored-by: pankajroark <pankajroark@users.noreply.github.com>
```
  a5375adc
- chore: update flashinfer v0.2.1.post2 (#3644) · 75d171a9
  Yineng Zhang authored Feb 18, 2025
  
  75d171a9
- feat: support flashinfer mla with prefix cache (#3643) · 714f3e63
  Yineng Zhang authored Feb 18, 2025
  
  714f3e63
- support multi-gpu block-gemm tuning (#3639) · c38f3aed
  Xiaoyu Zhang authored Feb 18, 2025
  
  c38f3aed
- fix Dockerfile.rocm · 2e6be53e
  Yineng Zhang authored Feb 17, 2025
  
  2e6be53e
- chore: bump v0.4.3.post1 (#3638) · e782eb7e
  Yineng Zhang authored Feb 17, 2025
  
  e782eb7e
- update unit test (#3636) · e319153b
  Yineng Zhang authored Feb 17, 2025
  
  e319153b
- add mtp unit test (#3634) · 32b44d2f
  Yineng Zhang authored Feb 17, 2025
  
  32b44d2f
- Revert "[ROCm] Use `tl.range()` in block GEMM kernels with `num_stage… (#3632) · 5f1a485d
  Yineng Zhang authored Feb 17, 2025
  
  5f1a485d
- [docker] added rdma support (#3619) · c9565e49
  Shenggui Li authored Feb 17, 2025
  
  c9565e49
- [docs] Update sampling_params.md (#3617) · d03c4c25
  Shi Shuai authored Feb 17, 2025
  
  d03c4c25
16 Feb, 2025 6 commits
- Draft of updated doc for sampling params. (#3260) · 8f13377d
  simveit authored Feb 16, 2025
```
Co-authored-by: shuaills <shishuaicareer@gmail.com>
```
  8f13377d
- Benchmark for reasoning models (#3532) · 3d4a8f9b
  simveit authored Feb 16, 2025
```
Co-authored-by: Chayenne <zhaochen20@outlook.com>
```
  3d4a8f9b
- Update to latest amd image. (#3597) · 7474bed8
  saienduri authored Feb 16, 2025
  
  7474bed8
- [ROCm] Use `tl.range()` in block GEMM kernels with `num_stages` set by host. (#3535) · 03caefeb
  Wen-Heng (Jack) Chung authored Feb 16, 2025
```
Co-authored-by: HAI <hixiao@gmail.com>
```
  03caefeb
- Model: Support Qwen 2.5 vl (#3258) · bcc213df
  Mick authored Feb 16, 2025
  
  bcc213df
- fix lockfile and port_registry file permission error (#3598) · 39416e39
  Jiada Li authored Feb 15, 2025
```
Co-authored-by: jiada li <jiada@lmsys.us-northcentral1-a.compute.internal>
Co-authored-by: zhaochenyang20 <zhaochen20@outlook.com>
```
  39416e39
15 Feb, 2025 6 commits
- [docs] added favicon to sphinx html (#3564) · 231c40d8
  Shenggui Li authored Feb 16, 2025
  
  231c40d8
- fix apply_token_bitmask_inplace_cuda (#3594) · bbc47c34
  Yineng Zhang authored Feb 15, 2025
  
  bbc47c34
- fix high qps crash when enable mtp (#3592) · dfce9269
  Yineng Zhang authored Feb 15, 2025
```
Co-authored-by: ispobock <ispobaoke@hotmail.com>
```
  dfce9269
- fix eagle unit test (#3591) · 6718b109
  Yineng Zhang authored Feb 15, 2025
  
  6718b109
- doc: emphasize and notify the usage of chat_template (#3589) · 7711ac6e
  Mick authored Feb 15, 2025
```
Co-authored-by: Chayenne <zhaochen20@outlook.com>
```
  7711ac6e
- [CI] Improve Docs CI Efficiency (#3587) · 7443197a
  Shi Shuai authored Feb 15, 2025
```
Co-authored-by: zhaochenyang20 <zhaochen20@outlook.com>
```
  7443197a
14 Feb, 2025 10 commits
- Support NextN (MTP) speculative decoding for DeepSeek-V3/R1 (#3582) · 862dd76c
  Ke Bao authored Feb 15, 2025
  
  862dd76c
- [fix] added support for vlm in offline inference (#3548) · fb4c9c3a
  Shenggui Li authored Feb 15, 2025
  
  fb4c9c3a
- ROCm docker: triton update (#3584) · d973c78e
  HAI authored Feb 14, 2025
  
  d973c78e
- Copy config files for MI300X to support in virtualized environments (#3505) · 6ce6eabb
  Jesse Lopez authored Feb 14, 2025
  
  6ce6eabb
- docs: update install (#3581) · 4e23c961
  Yineng Zhang authored Feb 14, 2025
  
  4e23c961
- fix sgl-kernel codestyle (#3563) · 3efbdf68
  Xiaoyu Zhang authored Feb 14, 2025
  
  3efbdf68
- Add support for OpenAI API o1 model (#3363) · 6cc30955
  Chuyue Sun authored Feb 13, 2025
```
Co-authored-by: Shan Yu <shanyu1@g.ucla.edu>
```
  6cc30955
- fix doc (#3558) · 31eec35b
  Yineng Zhang authored Feb 14, 2025
  
  31eec35b
- update flashinfer-python (#3557) · ac963be2
  Yineng Zhang authored Feb 14, 2025
  
  ac963be2
- chore: bump v0.4.3 (#3556) · e0b9a423
  Yineng Zhang authored Feb 14, 2025
  
  e0b9a423