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 supported26 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [Parser][0/N] Add unified Mistral parser entrypoint
- [Feature] TRITON_ATTN add INT8 per-tensor KV cache quantization
- fix: default TILELANG_CLEANUP_TEMP_FILES=1 to avoid shared /tmp conflicts
- Revert "[Attention] Abstract the MLA prefill backends and eliminate cuDNN" (#32623)
- [Bugfix] Fix hybrid Mamba KV cache allocation with request-constant pools
- [Perf] Batch Weight Prefetching via cuMemcpyBatchAsync to Reduce Latency
- [Bugfix][Gemma 4] Allow loading fine-tuned E2B/E4B checkpoints
- fix(v1): avoid false shutdown failures on clean exit
- [Performance]: Llama-Nemotron embedding is slower than Transformers for offline batch-32 pooling after compile-cache warmup
- [Tracking] TurboQuant + Gemma 4 multimodal: 5-gate blocker stack
- Docs
- Python not yet supported