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 supported61 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Bugfix] Keep the top-p filter on one kernel path under batch invariance
- [Bugfix][Attention] Accept split KV blocks in the b12x backend
- [Kernel][Perf] Bound DSA candidate mask writes to each row's extent
- [Bugfix] Make PyTorch top-k tie-breaking deterministic
- [Bug]: HF3FSKVConnector ignores hf3fs_metadata_server_url (both metadata clients use localhost:18000)
- [Feature]: HF3FSKVConnector: support models with more than one KV cache shape (e.g. MLA + DSA indexer)
- [Bugfix][KV Events] Close ZMQ sockets from publisher thread
- [Bugfix][KV Connector] Allocate HF3FS pages only for distinct misses
- [Bugfix] Handle unused scatter-split outputs
- [KVConnector][Mooncake] Detect shared-prefix junctions in the MooncakeStore lookup
- Docs
- Python not yet supported