COMMITS
/ core/config/gguf.go May 16, 2026
L
feat(llama-cpp): bump to MTP-merge SHA and automatically set MTP defaults (#9852)
LocalAI [bot] committed
April 21, 2026
L
Respect explicit reasoning config during GGUF thinking probe (#9463)
leinasi2014 committed
April 18, 2026
E
fix(vision): propagate mtmd media marker from backend via ModelMetadata (#9412)
Ettore Di Giacinto committed
March 21, 2026
E
feat: inferencing default, automatic tool parsing fallback and wire min_p (#9092)
Ettore Di Giacinto committed
March 20, 2026
E
chore(deps): bump llama-cpp to 'a0bbcdd9b6b83eeeda6f1216088f42c33d464e38' (#9079)
Ettore Di Giacinto committed
March 8, 2026
E
feat(functions): add peg-based parsing and allow backends to return tool calls directly (#8838)
Ettore Di Giacinto committed
February 1, 2026
E
fix: drop gguf VRAM estimation (now redundant) (#8325)
Ettore Di Giacinto committed
January 22, 2026
E
feat: detect thinking support from backend automatically if not explicitly set (#8167)
Ettore Di Giacinto committed
January 20, 2026
E
fix(reasoning): support models with reasoning without starting thinking tag (#8132)
Ettore Di Giacinto committed
December 21, 2025
E
chore(refactor): move logging to common package based on slog (#7668)
Ettore Di Giacinto committed
November 7, 2025
E
feat(llama.cpp): consolidate options and respect tokenizer template when enabled (#7120)
Ettore Di Giacinto committed
August 14, 2025
E
feat(backends): add system backend, refactor (#6059)
Ettore Di Giacinto committed
May 3, 2025
E
fix(gpu): do not assume gpu being returned has node and mem (#5310)
Ettore Di Giacinto committed
May 2, 2025
E
feat(llama.cpp): estimate vram usage (#5299)
Ettore Di Giacinto committed
March 29, 2025
E
feat(gguf): guess default context size from file (#5089)
Ettore Di Giacinto committed