Ettore Di Giacinto 800f749c7b fix: drop gguf VRAM estimation (now redundant) (#8325) ... fix: drop gguf VRAM estimation Cleanup. This is now handled directly in llama.cpp, no need to estimate from Go. VRAM estimation in general is tricky, but llama.cpp ( 41ea26144e/src/llama.cpp (L168) ) lately has added an automatic "fitting" of models to VRAM, so we can drop backend-specific GGUF VRAM estimation from our code instead of trying to guess as we already enable it 397f7f0862/backend/cpp/llama-cpp/grpc-server.cpp (L393) Fixes: https://github.com/mudler/LocalAI/issues/8302 See: https://github.com/mudler/LocalAI/issues/8302#issuecomment-3830773472		2026-02-01 17:33:28 +01:00
..
application_config.go	feat(api): add support for open responses specification (#8063)	2026-01-17 22:11:47 +01:00
application_config_test.go	feat(watchdog): add Memory resource reclaimer (#7583)	2025-12-16 09:15:18 +01:00
config_suite_test.go	dependencies(grpcio): bump to fix CI issues (#2362)	2024-05-21 14:33:47 +02:00
gallery.go	refactor: gallery inconsistencies (#2647)	2024-06-24 17:32:12 +02:00
gguf.go	fix: drop gguf VRAM estimation (now redundant) (#8325)	2026-02-01 17:33:28 +01:00
guesser.go	chore(refactor): move logging to common package based on slog (#7668)	2025-12-21 19:33:13 +01:00
model_config.go	chore: drop bark which is unmaintained (#8207)	2026-01-25 09:26:40 +01:00
model_config_filter.go	fix(config): make syncKnownUsecasesFromString idempotent (#7493)	2025-12-09 21:08:22 +01:00
model_config_loader.go	feat: detect thinking support from backend automatically if not explicitly set (#8167)	2026-01-23 00:38:28 +01:00
model_config_test.go	fix: propagate validation errors (#7787)	2025-12-30 09:54:27 +01:00
model_test.go	feat: Add Agentic MCP support with a new chat/completion endpoint (#6381)	2025-10-05 17:51:41 +02:00
runtime_settings.go	feat(api): add support for open responses specification (#8063)	2026-01-17 22:11:47 +01:00