Commits · 5ef545e6789da24cf2c86c189846211a0bc664a4 · change / sglang

22 Aug, 2025 6 commits
- [router] Move all protocols to spec.rs file (#9519) · 5ef545e6
  Keyang Ru authored Aug 22, 2025
  
  5ef545e6
- [router] add json tool parser (#9516) · f556ac8b
  Simo Lin authored Aug 22, 2025
  
  f556ac8b
- [router] tokenizer arch doc (#9513) · 49f9d025
  Simo Lin authored Aug 22, 2025
  
  49f9d025
- [router] fix router load guard tracking for streaming (#9491) · 0f8cee8c
  Simo Lin authored Aug 21, 2025
  
  0f8cee8c
- [router] add tool parser base structure and partial json parser (#9482) · 816c4c85
  Chang Su authored Aug 21, 2025
  
  816c4c85
- [router] remove all tokenizer metrics for performance (#9474) · 53e2cd46
  Chang Su authored Aug 21, 2025
  
  53e2cd46
21 Aug, 2025 2 commits
- [router] add glm and step3 reasoning parser (#9415) · 5cfbb4c1
  Chang Su authored Aug 20, 2025
  
  5cfbb4c1
- [router] Add IGW (Inference Gateway) Feature Flag (#9371) · 3828db43
  Keyang Ru authored Aug 20, 2025
```
Co-authored-by: Yineng Zhang <me@zhyncs.com>
```
  3828db43
20 Aug, 2025 2 commits
- [router] Implement OpenAI Responses API specification (#9367) · 5ae5ecaa
  Keyang Ru authored Aug 19, 2025
  
  5ae5ecaa
- [router] add tokenizer chat template support (#9370) · 5fbad308
  Simo Lin authored Aug 19, 2025
```
Co-authored-by: Chang Su <chang.s.su@oracle.com>
```
  5fbad308
19 Aug, 2025 7 commits
- [router] Implement gRPC SGLangSchedulerClient (#9364) · 7638f5e4
  Chang Su authored Aug 19, 2025
  
  7638f5e4
- [router] adds reasoning parser pooling and thread-safe (#9360) · b45f753c
  Simo Lin authored Aug 19, 2025
  
  b45f753c
- [Router] Add validation module for API parameters (#9335) · c5057262
  Keyang Ru authored Aug 19, 2025
  
  c5057262
- [router] add tiktokenizer and sequence in router (#9354) · 0b95a01a
  Simo Lin authored Aug 19, 2025
```
Co-authored-by: Chang Su <chang.s.su@oracle.com>
```
  0b95a01a
- [router] add dsr1, kimi, and qwen reasoning parser (#9353) · 94959237
  Simo Lin authored Aug 19, 2025
  
  94959237
- [router]restructure protocol modules for better organization (#9321) · ce67b2d5
  Keyang Ru authored Aug 18, 2025
  
  ce67b2d5
- [router] Add spec for sglang scheduler (#9322) · 439df454
  Chang Su authored Aug 18, 2025
  
  439df454
18 Aug, 2025 3 commits
- [router] add reasoning parser base structure (#9310) · 6e316588
  Simo Lin authored Aug 18, 2025
```
Co-authored-by: Chang Su <chang.s.su@oracle.com>
```
  6e316588
- [router] add tokenizer metrics (#9307) · 24247b41
  Simo Lin authored Aug 18, 2025
```
Co-authored-by: Chang Su <chang.s.su@oracle.com>
```
  24247b41
- [router] tokenizer factory, hf tokenizer, and stop sequence detector (#9293) · d08663ee
  Simo Lin authored Aug 17, 2025
```
Co-authored-by: Chang Su <chang.s.su@oracle.com>
```
  d08663ee
17 Aug, 2025 4 commits
- [router] introducing tokenizer trait (#9287) · ff0cf51c
  Simo Lin authored Aug 17, 2025
  
  ff0cf51c
- [router] introduce prefill response draining for http compliance (#9281) · b341b7db
  Simo Lin authored Aug 17, 2025
  
  b341b7db
- [router] add cargo clippy in CI and fix-up linting errors (#9242) · ce3ca9b0
  Jeff Nettleton authored Aug 17, 2025
  
  ce3ca9b0
- [router] fix pd prefill http request complinace issue (#9237) · bb10e3a1
  Simo Lin authored Aug 16, 2025
  
  bb10e3a1
15 Aug, 2025 3 commits
- [router] preserve original worker response header in router (#9236) · da53e13c
  Simo Lin authored Aug 15, 2025
  
  da53e13c
- [router] clean up lint warnings with clippy execution (#9201) · d7e38b2f
  Jeff Nettleton authored Aug 15, 2025
  
  d7e38b2f
- [router] allow more health check configuration (#9198) · 21b88460
  Simo Lin authored Aug 15, 2025
  
  21b88460
12 Aug, 2025 1 commit
- [router] Add Rust Binary Entrypoint for SGLang Router (#9089) · 9d68bdb2
  Simo Lin authored Aug 11, 2025
  
  9d68bdb2
11 Aug, 2025 3 commits
- refactor(pd-router): extract common patterns to reduce code duplication (#9081) · 38907fe6
  Simo Lin authored Aug 11, 2025
  
  38907fe6
- [pd-router] add retry and circuit breakfor for pd router (#9051) · 6f81a710
  Simo Lin authored Aug 11, 2025
  
  6f81a710
- [router] regular router circuit breaker (#8997) · 067068f2
  Simo Lin authored Aug 10, 2025
  
  067068f2
10 Aug, 2025 2 commits
- [router] upgrade kube version to latest (#9018) · 473400e4
  Simo Lin authored Aug 09, 2025
  
  473400e4
- [router] upgrade rand to latest version (#9017) · dd665f96
  Simo Lin authored Aug 09, 2025
  
  dd665f96
08 Aug, 2025 6 commits
- [router] fix radix tree integration issues in PD router (#8982) · 7b7e5615
  Simo Lin authored Aug 08, 2025
  
  7b7e5615
- [router] reduce contention, fix double-count race (#8978) · 1a8706c8
  Simo Lin authored Aug 08, 2025
  
  1a8706c8
- [router] add metrics for worker and policy (#8971) · 36bfddec
  Tony Lu authored Aug 09, 2025
```
Signed-off-by: Tony Lu <tonyluj@gmail.com>
```
  36bfddec
- [router] harden retries + metrics; fix streaming load; header filtering (#8972) · a59cbea9
  Simo Lin authored Aug 08, 2025
  
  a59cbea9
- [router] router circuit breaker core (#8941) · 61a46804
  Simo Lin authored Aug 08, 2025
  
  61a46804
- [router] dedicated prefill HTTP client and request-path optimizations (#8923) · 2e901e89
  Simo Lin authored Aug 07, 2025
  
  2e901e89
07 Aug, 2025 1 commit

refactor(sgl-router): Replace `once_cell` with `LazyLock` in worker.rs and... · fd05b567

Tien Nguyen authored Aug 07, 2025

refactor(sgl-router): Replace `once_cell` with `LazyLock` in worker.rs and remove once_cell dependency from Cargo.toml (#8698)

fd05b567