david/aphrodite-engine: PygmalionAI's large-scale inference engine pygmalion.chat It is designed to serve as the inference endpoint for the PygmalionAI website, and to allow serving the Pygmalion models to a large number of users with blazing fast speeds (thanks to vLLM's Paged Attention). @ sampling-kernels

AlpinDale ba371fbbbd feat: AWQ marlin kernels (#603)		il y a 4 mois
..
compressed_tensors	ba371fbbbd feat: AWQ marlin kernels (#603)	il y a 4 mois
gguf_utils	9d81716bfd [v0.5.3] Release Candidate (#388)	il y a 8 mois
utils	ba371fbbbd feat: AWQ marlin kernels (#603)	il y a 4 mois
__init__.py	ba371fbbbd feat: AWQ marlin kernels (#603)	il y a 4 mois
aqlm.py	9be43994fe feat: fbgemm quantization support (#601)	il y a 4 mois
autoquant.py	9be43994fe feat: fbgemm quantization support (#601)	il y a 4 mois
awq.py	9be43994fe feat: fbgemm quantization support (#601)	il y a 4 mois
awq_marlin.py	ba371fbbbd feat: AWQ marlin kernels (#603)	il y a 4 mois
base_config.py	9be43994fe feat: fbgemm quantization support (#601)	il y a 4 mois
bitsandbytes.py	9be43994fe feat: fbgemm quantization support (#601)	il y a 4 mois
deepspeedfp.py	9be43994fe feat: fbgemm quantization support (#601)	il y a 4 mois
eetq.py	9be43994fe feat: fbgemm quantization support (#601)	il y a 4 mois
exl2.py	9be43994fe feat: fbgemm quantization support (#601)	il y a 4 mois
fbgemm_fp8.py	408ca43d2e feat: support fbgemm_fp8 quant on ampere	il y a 4 mois
fp8.py	9be43994fe feat: fbgemm quantization support (#601)	il y a 4 mois
gguf.py	9be43994fe feat: fbgemm quantization support (#601)	il y a 4 mois
gptq.py	9be43994fe feat: fbgemm quantization support (#601)	il y a 4 mois
gptq_marlin.py	ba371fbbbd feat: AWQ marlin kernels (#603)	il y a 4 mois
gptq_marlin_24.py	9be43994fe feat: fbgemm quantization support (#601)	il y a 4 mois
hadamard.safetensors	9d81716bfd [v0.5.3] Release Candidate (#388)	il y a 8 mois
marlin.py	9be43994fe feat: fbgemm quantization support (#601)	il y a 4 mois
quip.py	9be43994fe feat: fbgemm quantization support (#601)	il y a 4 mois
quip_utils.py	9d81716bfd [v0.5.3] Release Candidate (#388)	il y a 8 mois
schema.py	9d81716bfd [v0.5.3] Release Candidate (#388)	il y a 8 mois
squeezellm.py	9be43994fe feat: fbgemm quantization support (#601)	il y a 4 mois