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 supported36 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [RFC]: Waiting-Queue-Informed LRU for Prefix Cache Eviction
- [Bug]: Hang in CUDA Graph replay with PyTorch symmetric-memory all-reduce when profiling with Nsight Systems
- [Core] Waiting-Queue-Informed LRU for Prefix Cache Eviction
- [Bug]: Deferred block-free path loses per-group eviction ordering for hybrid KV cache configs
- [Bug]: cuBLAS NVFP4 GEMM silently rejects M < 128, impacts speech model decode
- [Bug]: Missing quant_config in MTP eh_proj causes severe silent precision loss during W8A8 quantization
- [Bug][Spec Decode] num_speculative_tokens_per_batch_size + MTP speculator fails full CUDA graph decode capture (InputBatch.make_dummy assert)
- [Bug][Spec Decode] Drafter attention backend auto-selection picks FlashInfer on SM90 for a sliding-window drafter, hitting the guard crash
- [Performance] Add Triton kernel for Gemma3n sparse GELU
- [BugFix] Honor drop_eagle_block in MambaManager
- Docs
- Python not yet supported