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 supported51 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- Fix OverflowError in prompt_logprobs when external KV pre-fills prompt
- Add external metrics providers for stat logger plugins
- [ROCm][Bugfix] Hoist tt.addptr out of scf.if in fused_qk_rmsnorm
- [Bugfix] Fix DeepSeek MoE sequence-parallel layout tracking
- [Spec Decode] Fix FA3 AOT scheduler head count mismatch for DFlash/DSpark
- Rust Frontend: Add supervisor-side control channel for Elastic EP scaling
- Update workflow comments and add first-interaction action.
- [Bug]: sm_120 + local CUDA toolkit < 12.9: FlashInfer JIT failures kill engine init in three default paths (sampler, fused-MoE, FP8 KV) instead of falling back
- [Bug] Speculative decoding with a large num_speculative_tokens fails with a bare negative max_num_scheduled_tokens instead of naming the flags that fix it
- [Bug]: NixlConnector rejects packed hybrid KV cache after HMA rewrites block size
- Docs
- Python not yet supported