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 supported37 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- Bump the minor-update group across 1 directory with 170 updates
- [Bug]: `fused_qk_norm_rope` multi-head-per-warp kernel corrupts partial-NeoX (`rotary_dim < head_dim`) QK-Norm models on SM90
- [ROCm][MLA] TritonMLA: support causal multi-token decode
- [Bug]: OffloadingConnector can silently return wrong output at exact chunk boundaries with mamba_cache_mode=all
- [Perf][MoE] Optimize deepep_v2 receiver CPU Overhead
- [CI Failure]: test_mha_attn_varlen_forward_aiter_fp8 — "invalid argument for fmha_fwd" on MI300X
- [Bug]: `enable_prompt_embeds` + `enable_lora` on Llama crashes with `illegal memory access` under concurrency
- [Bugfix] Reject duplicate ranks in tiktoken vocab files
- AITER is not enabled on RDNA3 (gfx1100) — integration gap between CDNA3 and RDNA4
- [Bugfix][Multimodal] Invalidate retained PyNvVideoCodec decoder after failure
- Docs
- Python not yet supported