Popular repositories Loading

1. wmma-flashattention-v2 wmma-flashattention-v2 Public

   An optimized Flash-Attention-v2 kernel based on WMMA API

   Cuda

2. Parallel-GAE Parallel-GAE Public

   Parallel implementation of GAE for long-horizon RL. 65M tokens in ~1ms on A100.

   Cuda

3. flashinfer flashinfer Public

   Forked from flashinfer-ai/flashinfer

   FlashInfer: Kernel Library for LLM Serving

   Python

4. vllm vllm Public

   Forked from vllm-project/vllm

   A high-throughput and memory-efficient inference and serving engine for LLMs

   Python

5. sglang sglang Public

   Forked from sgl-project/sglang

   SGLang is a high-performance serving framework for large language models and multimodal models.

   Python