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 supported62 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Perf][Frontend] Serialize completion responses without an intermediate dict
- [DNM][CI bisect] Revert #55891 to identify FT E2E detection hang
- [Bugfix][Tokenizer] Align v4/v32 DSML argument handling with v41
- [Bugfix] Include specialize_active_lora in LoRAConfig.compute_hash
- [AuxOutput] Keep routed experts while a KV cache tier caches their blocks
- [Bugfix] Include disable_hybrid_kv_cache_manager in SchedulerConfig.compute_hash
- [Bugfix] Include draft execution fields in SpeculativeConfig.compute_hash
- [Bugfix] Parse human-readable ints with Decimal to avoid off-by-one
- [Bugfix] Reset num_compiled_artifacts_loaded in reset_compile_wrapper
- [Bugfix] Offset ipc:// endpoints in ZmqEventPublisher.offset_endpoint_port
- Docs
- Python not yet supported