Skip to content

Pull requests: sgl-project/sglang-omni

New pull request New
47 Open 230 Closed
47 Open 230 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Reviews
Filter by reviews
No reviews Review required Approved review Changes requested
Assignee
Filter by who’s assigned
Assigned to nobody Loading
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

[CI] Calibrate v1 thresholds for cuda graph at 2026.05.06 run-ci Triggers GPU CI workflows
#403 opened May 6, 2026 by zhaochenyang20 Collaborator Loading…
2
[V1]: Isolate IPC endpoints per server run run-ci Triggers GPU CI workflows
#402 opened May 6, 2026 by Ratish1 Collaborator Loading…
8
Add SGLang-Omni Router for V1
#401 opened May 6, 2026 by Ratish1 Collaborator • Draft
[Skill] Add running-eval-suite for refreshing reference benchmark
#400 opened May 6, 2026 by yxs Collaborator Loading…
11
[Refactor] Remove unused ModelWorker.get_worker_info run-ci Triggers GPU CI workflows
#399 opened May 5, 2026 by kevin85421 Contributor Loading…
5 tasks
2
[RFC] V1 unit test rewrite top-down
#397 opened May 5, 2026 by JingwenGu0829 Collaborator • Draft
2
[Bugfix] S2-Pro: probe vocoder GPU peak to auto-size mem_fraction_static, fixing 24 GB OOM
#391 opened May 4, 2026 by leohuang257 Loading…
2 of 5 tasks
1
6
[V1, Feature] Add OpenAI Realtime WebSocket endpoint (M0)
#385 opened May 4, 2026 by PopSoda2002 Collaborator • Draft
2
Fix installation instructions for Python 3.13 incompatibility and improve the sanity check example run-ci Triggers GPU CI workflows
#381 opened May 3, 2026 by kevin85421 Contributor Loading…
5 tasks
2
[v1]: Add v1 mirrors for unit tests run-ci Triggers GPU CI workflows
#380 opened May 3, 2026 by Ratish1 Collaborator Loading…
[Feat] add streaming TTS and test to Ming Omni run-ci Triggers GPU CI workflows
#378 opened May 3, 2026 by edwingao28 Collaborator Loading…
3 of 5 tasks
1
[S2-v1]: Add S2-Pro Streaming Vocoder run-ci Triggers GPU CI workflows
#374 opened Apr 29, 2026 by Ratish1 Collaborator Loading…
22
Add a PR-ready SocialOmni benchmark path for sglang-omni run-ci Triggers GPU CI workflows
#352 opened Apr 25, 2026 by Alexisxty Loading…
4 tasks done
7
[WIP][CI] Add CI for Ming Omni
#348 opened Apr 25, 2026 by edwingao28 Collaborator Loading…
3 of 5 tasks
1
[Ming-Omni] Support diffusion based image generation
#336 opened Apr 23, 2026 by yuan-luo Collaborator Loading…
5 tasks
1
2
[Perf] Qwen3-Omni audio encoder: sglang-native + CUDA-graph wrapper (up to 6.4x)
#333 opened Apr 22, 2026 by jiaoew1991 Loading…
3 of 5 tasks
8
add zh_CN document
#321 opened Apr 19, 2026 by LinJianan Loading…
1 of 5 tasks
[CLI] Expose --cpu-offload-gb, --tp-size, and --mem-fraction-static on sgl-omni
#308 opened Apr 17, 2026 by edwingao28 Collaborator Loading…
2 of 5 tasks
1
[WIP] Realtime websocket API
#282 opened Apr 13, 2026 by CTKnight • Draft
4 of 5 tasks
2
Implement TP for qwen3 omni model
#266 opened Apr 7, 2026 by qqwqqw689 Loading…
2
[devcontainer] Add devcontainer setup
#259 opened Apr 6, 2026 by CTKnight Loading…
1 of 5 tasks
2
feat: expose quantization and kv_cache_dtype in server args builder
#246 opened Mar 31, 2026 by ZhitongGuo Loading…
[WIP]feat: support flexible inference path for omni model
#241 opened Mar 31, 2026 by Hangzhi Loading…
3 tasks done
1
6
[Qwen3-Omni] Fix concurrent request CUDA crash in speech pipeline
#240 opened Mar 31, 2026 by ischencheng Contributor Loading…
1
[Feature] Framework-level torch.compile for S2-Pro codebook decoder Phase 1
#239 opened Mar 31, 2026 by yxs Collaborator Loading…
6
ProTip! no:milestone will show everything without a milestone.