Speed
5 items across the graph — tagged with Speed.
From the graph · 5
repo
LMCache/LMCache
→repoLMCache: Supercharge Your LLM with the Fastest KV Cache Layer
InternLM/lmdeploy
→repoLMDeploy is a toolkit for compressing, deploying, and serving LLMs.
kvcache-ai/Mooncake
→repoMooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.
lightseekorg/tokenspeed
→repoTokenSpeed is a speed-of-light LLM inference engine.
lightseekorg/TorchSpec
→A PyTorch native library for training speculative decoding models
