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 supported24 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [WIP] Fix MRV2 spec decoding when target and draft have different num attention heads
- add prot available check when create server before
- [BugFix][ROCM] Align the block size of rocm_attn kernel in hybrid attention arch.
- [Build][Attention] Degrade cleanly without flash-attn extensions
- [Hybrid] Warmup Mamba2 SSD kernel
- [CUDA][XPU]Enable triton version flash_attn_varlen_func for Triton MLA
- [Bug]: --reasoning-parser gemma4: streaming leaks reasoning into content after tool results in multi-turn conversations
- [Bugfix] Fix use_existing_torch.py removing unrelated packages
- [Bugfix] Add batched experts auto-upgrade for VLLM_FLASHINFER_MOE_BACKEND path
- fix: create DeepGEMM JIT cache directory before import
- Docs
- Python not yet supported