sglang
https://github.com/sgl-project/sglang
Python
SGLang is a high-performance serving framework for large language models and multimodal models.
Triage Issues!
When you volunteer to triage issues, you'll receive an email each day with a link to an open issue that needs help in this project. You'll also receive instructions on how to triage issues.
Triage Docs!
Receive a documented method or class from your favorite GitHub repos in your inbox every day. If you're really pro, receive undocumented methods or classes and supercharge your commit history.
Python not yet supported1 Subscribers
Add a CodeTriage badge to sglang
Help out
- Issues
- fix: do not override SGLANG_FLASHINFER_WORKSPACE_SIZE when user explicitly sets it
- [Bug] Scheduler event loop blocks on Mamba eviction under large-context requests, causing server hang and process kill
- Skip mamba middle chunks
- [perf] Vectorize text-only extend mrope position computation
- [DONT REVIEW][WIP][AMD] Enable MLA DCP for aiter backend
- [spec decoding] Add context to draft-worker verify-input guard error
- ci: sweep stale /dev/shm in job teardown to prevent shm-leak SIGBUS
- Fix NIXL bootstrap handling for foreign traffic
- [Bug] sgl-model-gateway router rejects /v1/responses requests with tool type "custom" — openai-protocol crate out of sync with Python protocol.py
- [Feature] Investigate CUTLASS 4.6 dynamic Epilogue Fusions and IKET profiling
- Docs
- Python not yet supported