LokeshSN

Facing the same issue. Logs: .\llama.cpp\llama-server.exe -m .\Models\GGUFs\ggml-org\gpt-oss-120b\gpt-oss-120b-mxfp4-00001-of-00003.gguf -ngl 99 --threads -1 -c 20000 --jinja --reasoning-format none -ot '([1-5]+).ffn_.*_exps.=CPU' load_backend: loaded RPC backend from E:\EverythingAI\llama.cpp\ggml-rpc.dll ggml_vulkan: Found 2 Vulkan devices:...