This is the quantized version of ByteDance-Seed/cudaLLM-8B, which is committed to making large language models easier to deploy and use through model compression technology, realizing the concept of 'Let knowledge be used by everyone'.

Natural Language ProcessingGguf

cudaLLM-8B is a professional language model developed by ByteDance Seed, specifically designed to generate high-performance and syntactically correct CUDA kernel code. Built on the Qwen3-8B base model, it is trained through two stages of supervised fine-tuning and reinforcement learning, enabling it to assist developers in writing efficient GPU parallel programming code.

Natural Language ProcessingTransformersEnglish

Kevin 32B is a large language model developed by Cognition AI, supporting an ultra-long context (40960 tokens) and focusing on CUDA kernel generation and reinforcement learning tasks.

Natural Language ProcessingGguf

BigVGAN is a large-scale trained universal neural vocoder capable of high-quality mel-spectrogram to waveform conversion. The v2 version accelerates inference through custom CUDA kernels and expands training data diversity.