Commits · e846d95ef6bae64c50f144c187881d8a926473de · change / sglang

"docs/vscode:/vscode.git/clone" did not exist on "ce441f6bde971a4231e9178b8531b620e478bed3"

24 Jun, 2025 4 commits
- Fix MTP with Deepseek R1 Fp4 (#7376) · 15f34013
  Charles Chen authored Jun 23, 2025
  
  15f34013
- Fix RequestValidationError response format (#7487) · d04163b3
  Chang Su authored Jun 23, 2025
  
  d04163b3
- bugfix: Prevent global mutation of conv.stop_str across requests (#7347) · 7732bbe4
  huangtingwei authored Jun 24, 2025
```
Co-authored-by: Chang Su <chang.s.su@oracle.com>
```
  7732bbe4
- Perormance: Enable cuda graph for dp idle batch (#7269) · ed0a0b69
  u4lr451 authored Jun 24, 2025
```
Co-authored-by: austindeng <austindeng@tencent.com>
Co-authored-by: Cheng Wan <54331508+ch-wan@users.noreply.github.com>
Co-authored-by: ch-wan <cwan39@gatech.edu>
```
  ed0a0b69
23 Jun, 2025 10 commits
- Support weight loading without mmap (#7469) · e5afb88b
  Yuhong Guo authored Jun 24, 2025
  
  e5afb88b
- Quick fix for DeepGemm requant to also cover MTP. (#7378) · e5ddeb04
  Charles Chen authored Jun 23, 2025
  
  e5ddeb04
- [perf] slightly imporve DeepSeek-R1-FP4 TP8 (#7481) · bdbb8d00
  JieXin Liang authored Jun 24, 2025
  
  bdbb8d00
- Fix dtype for idle input in spec decoding (#7456) · f8d48fd3
  Cheng Wan authored Jun 23, 2025
  
  f8d48fd3
- feat(func_call): Add more check in `BaseFormatDetector.parse_streaming_increment` (#7479) · 34b6b842
  Chang Su authored Jun 23, 2025
  
  34b6b842
- Fix prefill OOM due to wrong token calculation when page > 1 (#7397) · 25549433
  Liangsheng Yin authored Jun 24, 2025
  
  25549433
- Fix a bug in BatchTokenIDOut & Misc style and dependency updates (#7457) · 55e03b10
  Lianmin Zheng authored Jun 23, 2025
  
  55e03b10
- feat: integrate deepgemm into EPMoE (#6821) · 506c4928
  xutizhou authored Jun 23, 2025
```
Co-authored-by: tianqilin.99 <tianqilin.99@bytedance.com>
Co-authored-by: TianQiLin666666 <1834987979@qq.com>
Co-authored-by: Cheng Wan <54331508+ch-wan@users.noreply.github.com>
```
  506c4928
- Fix CUDA Graph Check under Deepep with DP FFN (#7451) · ac5010e0
  Cheng Wan authored Jun 22, 2025
  
  ac5010e0
- add fused moe config for qwen3 in triton3.3.1 (#7445) · 3cee035e
  Yi Zhang authored Jun 23, 2025
  
  3cee035e
22 Jun, 2025 5 commits
- Fix torch compile run (#7391) · bd4f5818
  kk authored Jun 23, 2025
```
Co-authored-by: wunhuang <wunhuang@amd.com>
Co-authored-by: Sai Enduri <saimanas.enduri@amd.com>
```
  bd4f5818
- Remove copy after bmm (#7441) · 50f1b6d6
  Ke Bao authored Jun 23, 2025
  
  50f1b6d6
- FlashInfer NVFP4 MoE with EP & 2-stream shared expert (#7327) · 5962e70d
  Trevor Morris authored Jun 22, 2025
```
Co-authored-by: JieXin Liang <Alcanderian@users.noreply.github.com>
Co-authored-by: alcanderian <alcanderian@gmail.com>
```
  5962e70d
- Tiny add logging for GC (#7406) · edc21cc8
  fzyzcjy authored Jun 22, 2025
  
  edc21cc8
- [minor] simplify the `TokenToKVPoolAllocator` (#7414) · 05c9bc89
  Liangsheng Yin authored Jun 22, 2025
  
  05c9bc89
21 Jun, 2025 9 commits
- Refactor LoRAManager and LoRAMemoryPool state management logic for dynamic... · 1998ce40
  Lifu Huang authored Jun 21, 2025
```
Refactor LoRAManager and LoRAMemoryPool state management logic for dynamic LoRA loading support (#7412)
```
  1998ce40
- feat(oai refactor): Replace `openai_api` with `entrypoints/openai` (#7351) · 72676cd6
  Chang Su authored Jun 21, 2025
```
Co-authored-by: Jin Pan <jpan236@wisc.edu>
```
  72676cd6
- [fix] PD disaggregation when enable mtp and tp!=dp (#7420) · 02bf31ef
  Atream authored Jun 22, 2025
  
  02bf31ef
- Fix CPU offloading for MLA memory pool (#7409) · 5ea5d221
  Liangsheng Yin authored Jun 22, 2025
  
  5ea5d221
- fix: Fix CI test_function_call_parser.py (#7425) · fdfd5224
  Chang Su authored Jun 21, 2025
  
  fdfd5224
- fix overlap pagecount (#6984) · 7f3ee861
  pansicheng authored Jun 21, 2025
```
Co-authored-by: Zhiqiang Xie <xiezhq@stanford.edu>
```
  7f3ee861
- [BugFix]fix qwen25 invoke function call streaming responses with curly braces... · bec58910
  ehuaa authored Jun 21, 2025
```
[BugFix]fix qwen25 invoke function call streaming responses with curly braces as the starting indicator (#7394)
```
  bec58910
- [BugFix]: fix EmbeddingReqInput single input error (#7396) · 9edf6608
  woodx authored Jun 21, 2025
  
  9edf6608
- [OAI Server Refactor] [ChatCompletions & Completions] Support Return Hidden State (#7329) · 5e7fdc79
  Keyang Ru authored Jun 20, 2025
```
Signed-off-by: keru <rukeyang@gmail.com>
```
  5e7fdc79
20 Jun, 2025 12 commits
- Fix 7285 Merge Conflicts (#7403) · 5041df2d
  Cheng Wan authored Jun 20, 2025
  
  5041df2d
- Update usage_processor.py (#7402) · 256801e9
  Cheng Wan authored Jun 20, 2025
  
  256801e9
- Optimize DP attn scheduling for speculative decoding (#7285) · 73b13e69
  Cheng Wan authored Jun 20, 2025
  
  73b13e69
- Fix All-Gather under world size one (#7219) · 8609e637
  Cheng Wan authored Jun 20, 2025
  
  8609e637
- [OAI Server Refactor] [ChatCompletions & Completions] Implement UsageInfo Processor (#7360) · dea2b84b
  yhyang201 authored Jun 21, 2025
```
Co-authored-by: Chang Su <chang.s.su@oracle.com>
```
  dea2b84b
- [OAI refactor] Add rerank and score serving (#7399) · cfb2fb5a
  woodx authored Jun 21, 2025
```
Co-authored-by: Chang Su <chang.s.su@oracle.com>
```
  cfb2fb5a
- [DeepSeekNextN] fix: residual of head norm can be None (#7398) · 22bfed75
  Cheng Wan authored Jun 20, 2025
  
  22bfed75
- [Feature] Comprehensive Hybrid Parallelism Support (#6389) · e879d8b7
  Cheng Wan authored Jun 20, 2025
  
  e879d8b7
- Refine OpenAI serving entrypoint to remove batch requests (#7372) · 09988080
  Xinyuan Tong authored Jun 20, 2025
```
Signed-off-by: Xinyuan Tong <justinning0323@outlook.com>
Co-authored-by: Chang Su <csu272@usc.edu>
```
  09988080
- Support THUDM/GLM-4-0414 (GLM-Z1) Glm4ForCausalLM architecture. (#5485) · 794be55a
  Wenbo Yang authored Jun 21, 2025
  
  794be55a
- [PD] Optimize custom mem pool usage and bump mooncake version (#7393) · 187b85b7
  Shangming Cai authored Jun 21, 2025
```
Signed-off-by: Shangming Cai <caishangming@linux.alibaba.com>
```
  187b85b7
- support return logprobs for pipeline (#7356) · ceba0ce4
  strgrb authored Jun 20, 2025
```
Co-authored-by: Zhang Kaihong <zhangkaihong.zkh@alibaba-inc.com>
```
  ceba0ce4