Inicio Explorar Axuda
Iniciar sesión
radu
/
LLamaRecipes
réplica de https://github.com/facebookresearch/llama-recipes.git
Seguir 1
Destacar 0
Fork 0
Ficheiros Incidencias 0 Wiki
Rama: dan/add-groq-recipes
Ramas Etiquetas
LLamaRecipes
/
recipes
/
benchmarks
/
inference_throughput
/
on-prem
/
vllm
Chester Hu 816b25fc8f Remove local tokenizer requirement for vllm on prem throughput benchmark hai 1 ano
..
chat_vllm_benchmark.py 816b25fc8f Remove local tokenizer requirement for vllm on prem throughput benchmark hai 1 ano
input.jsonl 367e4869ac Reorg inference throughput folder structure hai 1 ano
parameters.json 816b25fc8f Remove local tokenizer requirement for vllm on prem throughput benchmark hai 1 ano
pretrained_vllm_benchmark.py 816b25fc8f Remove local tokenizer requirement for vllm on prem throughput benchmark hai 1 ano