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
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Feature][ROCm] Enable gfx1030 (RDNA2) as a recognized RDNA arch
- [Bugfix] Enforce deterministic cuDNN convolution under VLLM_BATCH_INVARIANT
- [Core][Perf] Zero new KV blocks by cache group
- # [kimik3][ROCm] Enable torch.compile for so post-grad fusion passes work (aiter::fused_qk_rmsnorm_kernel, aiter::allreduce_fusion_kernel_1stage)
- [Mamba][Quantization] Add Stage 1 (CPU-only, reference) int8 quantization utilities for SSM state
- [RFC]: fp8_ds_mla KV cache on pre-SM89 (Ampere) GPUs via software-dequant TritonMLA decode
- [CI][Releases] Trigger `perf-eval` Through Release Pipeline
- [kimik3][ROCm][Perf] Fuse the MLA q/kv RMSNorm pair in the module forward
- [Tests] Centralize GSM8K eval definitions
- [Bugfix][NIXL] Fail closed on HMA receive errors
- Docs
- Python not yet supported