Completely broken?
#1
by zoyer - opened
Completely broken, not sure if i'm doing something wrong but on llama.cpp it's completely broken
OpenAI_GPT-OSS-120B_Pruned_REAP_58B-SafeTensors.i1-IQ4_XS.gguf --ctx-size 131072 -ngl 99 --flash-attn on --cache-type-k q4_1 --cache-type-v q4_1 --chat-template-file ~/llama.cpp/models/gpt-oss.jinja