Categories / LLM Infrastructure

Pure Rust + CUDA LLM inference engine — no PyTorch, OpenAI-compatible, serves Qwen3 to Kimi-K2

Last push 1 day ago

cudacuda-kernelsdeepseekgpuinferenceinference-enginekimikimi-k2kv-cachellmllm-inferencellm-servingmodel-servingmoeopenai-apipaged-attentionqwenqwen3rustvllm

Created

Feb 2026

Total stars

748

Last 7 days

0

Last 30 days

0

Last 12 months

0

README badge

Rusty Stars badge for pegainfer-project/pegainfer
[![Rusty Stars](https://rustystars.dev/badge/pegainfer-project/pegainfer.svg)](https://rustystars.dev/pegainfer-project/pegainfer)