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 supported46 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Core][Scheduler] Simulate reclaimable KV cache blocks before preempting running requests
- [Perf] Skip decode for generative scoring with max_tokens=0
- [Attention] Add HPC attention backend for improved performance on SM90 GPUS
- [Bug]: Crash on Transcription (size for tensor a must match the size of tensor b) with reproduce
- [ROCm] Fix UnboundLocalError for prefix_scheduler_metadata in Triton attention
- Fix Cohere ASR failing to load when librosa is not installed
- fix: allow HMA with KV events when explicitly enabled
- Fix engine_id collision + MoRIIO robustness for multi-node disagg DP
- WIP: SarvamMLAForCausalLM (begin work)
- [Bug]: Ngram speculative decoding produces corrupted output on hybrid GDN (Qwen3.5) models
- Docs
- Python not yet supported