Commits · 88bb627d0d224ad4195cc068cdca30f0b3634b48 · zhaoyu6 / sglang

"tools/vscode:/vscode.git/clone" did not exist on "5bbbb1d5c34d2a100431e80f3c4dfe0e09f41854"

09 Oct, 2025 7 commits
- [router][grpc] Replace fake health check with correct ones (#11387) · b520958e
  Chang Su authored Oct 09, 2025
  
  b520958e
- fix bench_serving mishandling of internal states (#11376) · fa7e2c30
  shaharmor98 authored Oct 09, 2025
```
Signed-off-by: Shahar Mor <smor@nvidia.com>
```
  fa7e2c30
- add code pp support for nixl (#11375) · 8f2cd177
  shaharmor98 authored Oct 09, 2025
```
Signed-off-by: Shahar Mor <smor@nvidia.com>
```
  8f2cd177
- [DeepSeek-V3.2] Include indexer kv cache when estimating kv cache size (#11309) · a4b424c6
  Trevor Morris authored Oct 08, 2025
  
  a4b424c6
- [router][grpc] disable health check generation and increase timeout (#11353) · 368fd206
  Simo Lin authored Oct 08, 2025
  
  368fd206
- [Generative Score API] Multi-Item scoring with custom attention mask. (#10979) · 53bd00d9
  Sundara Raman Ramachandran authored Oct 08, 2025
  
  53bd00d9
- [Auto Sync] Update scheduler.py (20251009) (#11350) · e22b13c5
  Yineng Zhang authored Oct 08, 2025
```
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
Co-authored-by: Junxiong Wang <junxiong@together.ai>
```
  e22b13c5
08 Oct, 2025 16 commits
- [router][grpc] Cleanup debug logs in grpc_server and grpc_router (#11340) · a65ca739
  Chang Su authored Oct 08, 2025
  
  a65ca739
- model: Support Hybrid Mamba2 NemotronHForCausalLM (nvidia/NVIDIA-Nemotron-Nano-9B-v2) (#10909) · d6837aea
  Netanel Haber authored Oct 08, 2025
```
Signed-off-by: Netanel Haber <nhaber@nvidia.com>
```
  d6837aea
- [CI] improve disaggregation CI. (#11264) · c882b5ae
  Liangsheng Yin authored Oct 08, 2025
```
Signed-off-by: Shangming Cai <csmthu@gmail.com>
Co-authored-by: Shangming Cai <csmthu@gmail.com>
```
  c882b5ae
- benchmark: enhance configurable multimodal benchmarking in bench_serving (#9812) · e3bb7f5a
  Kevin Xiang Li authored Oct 08, 2025
```
Co-authored-by: Xiang (Kevin) Li <lik@nvidia.com>
Co-authored-by: Xinyuan Tong <115166877+JustinTong0323@users.noreply.github.com>
```
  e3bb7f5a
- Support LoRA in bench_serving oai interface (#11318) · 92473e2e
  Lifu Huang authored Oct 08, 2025
  
  92473e2e
- fix(decode): adjust ServerArgs import to explicit module path (#11007) · 6c0bb327
  JinYan Su authored Oct 08, 2025
  
  6c0bb327
- [2/2] Support MHA prefill with FlashAttention 4. (#10937) · edefab0c
  Lifu Huang authored Oct 08, 2025
```
Co-authored-by: Hieu Pham <hyhieu@gmail.com>
```
  edefab0c
- Skip weight loading in deepgemm compilation (#11312) · 97cd38e5
  Cheng Wan authored Oct 07, 2025
  
  97cd38e5
- [8/N] MoE Refactor: deprecate `EPMoE` (#11211) · 3c06b673
  Cheng Wan authored Oct 07, 2025
  
  3c06b673
- [Feature] Add /tokenize and /detokenize OpenAI compatible endpoints (#9545) · 7c3f07db
  Adarsh Shirawalmath authored Oct 08, 2025
  
  7c3f07db
- Rename `ngram_utils` -> `ngram_info` (#11316) · 4b4dc132
  Liangsheng Yin authored Oct 08, 2025
  
  4b4dc132
- Optimize copy_kv_cache for spec decoding (#11126) · 5a9170d9
  YAMY authored Oct 08, 2025
```
Co-authored-by: Xinyuan Tong <115166877+JustinTong0323@users.noreply.github.com>
```
  5a9170d9
- [Chore] Update xgrammar 0.1.24 -> 0.1.25 (#10710) · 832c84fb
  DarkSharpness authored Oct 08, 2025
  
  832c84fb
- ci: unify the model launch method of nightly ci (#11230) · 64d1505c
  Mick authored Oct 08, 2025
  
  64d1505c
- Clean match_prefix and prepare_for_extend for mem cache V2 (#11200) · f3764c26
  cctry authored Oct 07, 2025
  
  f3764c26
- [oai serving chat] Add argument `--sampling-defaults` and fix... · 7ba3de0e
  Chang Su authored Oct 07, 2025
```
[oai serving chat] Add argument `--sampling-defaults` and fix `ChatCompletionRequest` defaults (#11304)
```
  7ba3de0e
07 Oct, 2025 14 commits
- [router][grpc] Fix request_id extraction when n > 1 (#11311) · f094e0a4
  Chang Su authored Oct 07, 2025
  
  f094e0a4
- [quantization] Properly ignore quantization for layers excluded in quant_config (#11205) · cd4b39a9
  Bowen Bao authored Oct 07, 2025
  
  cd4b39a9
- Update tool parser and related documentation (#11223) · e3c7f091
  Xinyuan Tong authored Oct 07, 2025
  
  e3c7f091
- [router][grpc] Fix sampling_params.stop_strs is None (#11306) · 6f1e03a4
  Chang Su authored Oct 07, 2025
  
  6f1e03a4
- [router] add get server info and get model info in grpc server (#11303) · 2fcd56ea
  Simo Lin authored Oct 07, 2025
  
  2fcd56ea
- Introduce future indices (#11301) · 3ddd7dc9
  Liangsheng Yin authored Oct 07, 2025
  
  3ddd7dc9
- Remove sampling info events and overlap thread file (#11300) · 501dfa6b
  Liangsheng Yin authored Oct 07, 2025
  
  501dfa6b
- Remove overlap thread (#11210) · 1519a89c
  Liangsheng Yin authored Oct 07, 2025
```
Co-authored-by: Lianmin Zheng <15100009+merrymercy@users.noreply.github.com>
Co-authored-by: Hanming Lu <69857889+hanming-lu@users.noreply.github.com>
```
  1519a89c
- EAGLE cache fix for SWARadixCache (#11231) · 24bc3fb0
  Ke Bao authored Oct 07, 2025
```
Co-authored-by: Hanming Lu <69857889+hanming-lu@users.noreply.github.com>
```
  24bc3fb0
- Feature/longbench v2 evaluation utils (#10949) · 533e58a1
  Al-Ekram Elahee Hridoy authored Oct 07, 2025
  
  533e58a1
- convert test_deterministic into unit tests (#11095) · 9b4c4497
  Alex Chi Z authored Oct 07, 2025
```
Signed-off-by: Alex Chi Z <iskyzh@gmail.com>
Co-authored-by: Baizhou Zhang <sobereddiezhang@gmail.com>
```
  9b4c4497
- [router][grpc] Fix proto3 default value mismatches and cleanup unused fields (#11283) · a578d300
  Chang Su authored Oct 06, 2025
  
  a578d300
- fix: correct scale parameter remapping logic in Llama4ForConditionalGeneration (#11282) · fd8a0b29
  Xinyuan Tong authored Oct 06, 2025
  
  fd8a0b29
- Fix LoRA support for multimodal models (VLMs) by implementing a consistent... · afc35ccc
  Chenxi Li authored Oct 06, 2025
```
Fix LoRA support for multimodal models (VLMs) by implementing a consistent pattern for skipping vision components (#11261)
```
  afc35ccc
06 Oct, 2025 3 commits
- Rename max_micro_batch_size -> pp_max_micro_batch_size (#11279) · 708f4ff4
  Lianmin Zheng authored Oct 06, 2025
  
  708f4ff4
- [Auto Sync] Update test_utils.py (20251006) (#11280) · e2daeb35
  Lianmin Zheng authored Oct 06, 2025
```
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
Co-authored-by: Sehoon Kim <sehoon@x.ai>
```
  e2daeb35
- Enable native ModelOpt quantization support (1/3) (#7149) · 155cbb51
  Zhiyu authored Oct 06, 2025
```
Signed-off-by: Zhiyu Cheng <zhiyuc@nvidia.com>
```
  155cbb51