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
- [BugFix] Synchronize Breakable CUDA Graph after warmup before capture
- fix(security): harden SafeUnpickler with exact-name allowlist for generic modules
- [Bug] DSpark compact ragged CUDA Graph uses incompatible request-slot geometry for the same token tier
- Remove many scheduler synchronization to enable overlap scheduler on agent workload
- [Bug] DSpark CUDA launch failure when concurrency=1 for Kimi-K3 (v0.5.17)
- [Bug] ROCm MI355 HiCache Broken - Poor Performance for Realistic Agentic Workload
- Fix guided decoding for channel-framed reasoning
- [NPU] Add npu_ipc support for mm_feature_transport
- [Metrics] Add kv_cache_usage_perc Prometheus gauge (#5979)
- [Bug] SGLANG_SIMULATE_ACC_LEN silently degrades detokenization to O(n²) ā `predict.fill_(100)` emits a byte-fallback token, and the `endswith("\ufffd")` commit gate then never advances the incremental-detokenization offsets
- Docs
- Python not yet supported