mixtral-inference icon indicating copy to clipboard operation
mixtral-inference copied to clipboard

inference code for mixtral-8x7b-32kseqlen

Results 1 mixtral-inference issues
Sort by recently updated
recently updated
newest added

Hi, Great repo! You mentioned you need quite a few A100s. If this model is ~50B parameters and ppl can run Llama 2 70B on 1xA100, why does this take...