Hugging Face's logo

amd
/
gpt-oss-20b-WFP8-AFP8-KVFP8

Safetensors
gpt_oss
quark
Model card Files
xet
Community
6
gpt-oss-20b-WFP8-AFP8-KVFP8 / tokenizer.json

Commit History

KV cache quantization in FP8 (#1)
73fc8ea
verified

XuebinWang commited on