llama.cpp on a jailbroken PS5: run any GGUF model natively on the console, starting with Qwen 3.8
Commits on main
App: ready only once the server serves metrics, not its 503 while the model loads
760bbf8 Mert Cobanov committed 1 month ago
App: Console page, the feed as a chat, Demo and Message, choice lists, one sound per action
559b637 Mert Cobanov committed 1 month ago
README: PS5LM, with decision models powered by Ollaya; docs/BUILDING.md
bd9f34b Mert Cobanov committed 1 month ago
App: a splash while the app restarts; the suggested 27B is UD-Q2_K_XL
390d7aa Mert Cobanov committed 1 month ago
App: driver and ggml switches from /data/PS5LM/env.txt; RADV patches
51eaac0 Mert Cobanov committed 1 month ago
llama.cpp patch 0006: tojson writes floats as Python does
e21a57d Mert Cobanov committed 1 month ago
llama.cpp 04f7226: decision models on /v1/systemone, MiniCPM-V 4.7
32a18d9 Mert Cobanov committed 1 month ago
Build: the ps5-opengl SDK through ps5-homebrew-ui's own script, build/ before configure
73182e2 Mert Cobanov committed 1 month ago
v0.8.0: downloads that survive lost connections, Downloads page, busy screen
fa0653d Abhiram committed 1 month ago
Merge feature/download-memory: drive space and download choices
81bcfd6 Abhiram committed 1 month ago