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
- [Bugfix][Spec Decode] Log EAGLE draft RoPE parameters at startup
- [ROCm][Misc] Write GDN prefill output in place for the Triton and FlyDSL backends
- [Model] Support ModernBERT decoder (Ettin) via the Transformers modeling backend
- [Core] Shared abstractions for specialized decode kernels
- [Perf][DSv4.1] Fuse C1/C2 compression with FP8 KV cache insertion
- [ROCm][CI][BugFix][AITER ON] Make LM Eval Small Models tests pass on MI300/MI355 and ensure they can work with vllm serve and vllm bench serve with AITER on and off
- [Perf][Attention] DiffKV prefill tiling on SM80: BLOCK_M=128 + KV tile 64 gives 3.0x on 200K-context chunks
- WIP: [Bugfix][Model] Preserve all Kimi-Audio embeddings in batched requests
- WIP: [Bugfix][ROCm] Preserve 64-bit QuickReduce phase offsets
- [Bug]: Severe output degeneration on SM120 with Apertus-70B FP8 in vLLM 0.25.1; v0.22.1 works after rollback
- Docs
- Python not yet supported