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 supported30 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- perf : Avoid per-step list+np.array allocation in _prepare_inputs by reusing input_batch.num_tokens_no_spec
- [Feature]: Improving NVFP4 Quantization via Fast and Accurate Sweep on FP8 Block Scale
- [Bug][OffloadingConnector] _blocks_being_loaded serialises concurrent requests through a single load, causing 12× TTFT inflation
- [Bugfix][OffloadingConnector] avoid request convoy when concurrent requests share blocks being loaded
- [Kernel][XPU] Add unit tests for FLA solve_tril and recompute_w_u_fwd
- [Bug]: GGUF model loading fails on XPU: `_C` namespace missing `ggml_dequantize` custom op
- [AMD] Support fp4 dispatch and fp8 combine for MORI EP
- [Bugfix] Reject non-positive num_gpu_blocks_override in CacheConfig
- [Bugfix][CI/Build] Fix Plamo2 HF runner crash on transformers v5 (_tied_weights_keys list→dict)
- fix(lora): _load_lora_config retry uses deterministic backoff without jitter — thundering herd risk
- Docs
- Python not yet supported