Pulse
0
Velocity
Stars
0
High-performance quantization and acceleration library for Qwen LLMs.
An optimization library designed to accelerate inference or training operations for Qwen LLM models.
Achieve lightning-fast inference for Qwen LLMs with advanced quantization and acceleration.
Why Trending
Significantly speeds up Qwen LLM inference on various hardware, improving deployment efficiency.
Target Audience
LLM developers, AI inference engineers.
Similar Projects