Whisper at 1.58 bits with custom kernels for edge inference

비슷한 프로덕트

설명이 비슷한 순

1. Open-source AMDGCN kernels for optimizing LLM inference

   github.com

   HNHacker News5점

2. KaniTTS

   huggingface.co

   Open-source high-fidelity TTS with just 450M params

   HNHacker News5점

3. Inferbench

   inferbench.com

   collect/share datapoints on GPU's inference performance

   HNHacker News7점

4. An RDMA/Infiniband Distributed Cache for Fast Inference and Training

   github.com

   A high-performance RDMA distributed file system for fast LLM Inference and GPU Training.

   HNHacker News13점

5. Phobos

   joa-ebert.com

   A tiny scale-free kernel language with tile-DAG support

   HNHacker News11점