vllm
https://github.com/vllm-project/vllm
Python
A high-throughput and memory-efficient inference and serving engine for LLMs
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 supported25 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- feat: support passing configuration to custom attention backends
- [Performance] Stagger checkpoint file reads across ranks to reduce I/O contention
- fix: prevent streaming sessions from exceeding max_model_len
- [SimpleCPUOffloadConnector]: Support cross layer KV layout
- [Scheduler] Priority scheduling supports preemption of requests in the running queue by requests in the waiting queue
- fix: auto-enable repetition detection for structured output requests
- [Bugfix] Auto-enable repetition detection for grammar-constrained structured output
- [Bug/Feature] TurboQuant + Hybrid MoE (Qwen3.6-35B-A3B) broken on Ampere (SM 80-86) — 13 patches with fixes
- [Bug]: `ROCM_AITER_MLA_SPARSE` prefill produces garbage for prompt_len > ~20K tokens on gfx950 (GLM-5.1-FP8)
- fix(vllm): port skip_kv_gather check and workspace reservation to ROCm MLA sparse attention
- Docs
- Python not yet supported