Popular repositories Loading

1. MIXQ MIXQ Public

   MIXQ: Taming Dynamic Outliers in Mixed-Precision Quantization by Online Prediction

   Python 94 15

2. vllm-mixed-precision vllm-mixed-precision Public

   Support mixed-precsion inference with vllm

   Python 85 19

3. MixQ_Tensorrt_LLM MixQ_Tensorrt_LLM Public

   Mixed precision inference by Tensorrt-LLM

   C++ 80 12

4. QComplier QComplier Public

   quantize mixed precision model

   C++ 10

5. SC24_MIXQ_AE SC24_MIXQ_AE Public

   Official implementation of MIXQ for AE

   HTML 3

6. AccText2Img AccText2Img Public

   Accelerate the text to image by mixed precsion computing

   Python