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 supported18 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [4/n] Migrate FP4/W4A8 CUTLASS kernels to torch stable ABI
- [ROCm] Enable MORI EP for unquantized MoE with AITER backend
- [Kernel] Add MXFP4 W4A4 CUTLASS MoE kernel for SM100
- [Bugfix] Fall back to Triton/FLA when system CUDA toolkit < 12.6 for GDN prefill kernel
- Fix NVFP4-quantized MoE checkpoint support for Step-3.5 Flash
- [Core][Metrics][BugFix] Replace num_cached_tokens/num_external_computed_tokens with PrefillStats
- [perf][cpu] Accelerate BF16 GELU with LUT impl on Arm CPUs
- [HMA]Move hybrid blksize to update_block_size_for_backend to fix attn supported block size is not 16 issue
- [KVCache] Support Pluggable KVCacheSpec
- refactor hard coded device string in test files under tests/v1 and tests/lora
- Docs
- Python not yet supported