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
- [Roadmap] Further Ngram Speculative Decoding Support
- [parallel state Refactor 3/n] Unify communicator interface
- [Perf] Tune EP-MOE permute kernel: BLOCK_SIZE=1024, num_warps=8
- [diffusion][ROCm] attention: Enable ring attention on the AITER backend
- fix(dp-attn): DP-attention buffer sizing + EAGLE padding for require_attn_tp_gather=True
- moe_kernels.py, stage-2 reduce path: small SGLANG_MORI_NUM_MAX_DISPATCH_TOKENS_PER_RANK silently corrupts output (gsm8k=0) at low concurrency
- [Apple Silicon][MLX] Fix scheduler OOM on long prompts and concurrent requests
- [router] Add --worker-api-key for introspection and KV-event discovery against api-key workers
- Refactor the selection of `--fp8-gemm-backend` with per-tensor and per-channel quantized models
- [RFC] Position-Independent KV Cache Reuse for Agentic/RAG Workloads
- Docs
- Python not yet supported