COMMITS
/ pkg/model/loader.go May 24, 2026
L
fix(distributed): route per request across loaded replicas + cache probeHealth (#9968)
LocalAI [bot] committed
April 26, 2026
E
fix(model-loader): also skip .ckpt, .zip, and .tag files when scanning models
Ettore Di Giacinto committed
April 8, 2026
E
fix(nodes): better detection if nodes goes down or model is not available (#9274)
Ettore Di Giacinto committed
March 29, 2026
E
feat: add distributed mode (#9124)
Ettore Di Giacinto committed
March 18, 2026
R
feat(ui): Per model backend logs and various fixes (#9028)
Richard Palethorpe committed
March 11, 2026
E
feat(ui): MCP Apps, mcp streaming and client-side support (#8947)
Ettore Di Giacinto committed
February 5, 2026
Y
fix: filter GGUF and GGML files from model list (#8397)
Yaroslav98214 committed
December 25, 2025
E
feat: disable force eviction (#7725)
Ettore Di Giacinto committed
December 21, 2025
E
chore(refactor): move logging to common package based on slog (#7668)
Ettore Di Giacinto committed
December 12, 2025
E
feat(loader): enhance single active backend to support LRU eviction (#7535)
Ettore Di Giacinto committed
November 20, 2025
E
feat(ui): runtime settings (#7320)
Ettore Di Giacinto committed
October 16, 2025
E
fix: guard from potential deadlock with requests in flight (#6484)
Ettore Di Giacinto committed
September 25, 2025
E
chore(models): add whisper-turbo via whisper.cpp (#6340)
Ettore Di Giacinto committed
August 16, 2025
E
feat(ui): General improvements (#6072)
Ettore Di Giacinto committed
August 14, 2025
E
feat(backends): add system backend, refactor (#6059)
Ettore Di Giacinto committed
June 15, 2025
E
feat: Add backend gallery (#5607)
Ettore Di Giacinto committed
May 16, 2025
O
fix: typos (#5376)
omahs committed
April 1, 2025
E
feat(loader): enhance single active backend by treating as singleton (#5107)
Ettore Di Giacinto committed
March 31, 2025
E
fix: race during stop of active backends (#5106)
Ettore Di Giacinto committed
January 16, 2025
E
feat(tts): Add Kokoro backend (#4616)
Ettore Di Giacinto committed
December 8, 2024
E
feat(template): read jinja templates from gguf files (#4332)
Ettore Di Giacinto committed
November 14, 2024
E
chore(api): return values from schema (#4153)
Ettore Di Giacinto committed
November 6, 2024
E
chore: hide raw safetensors files (#4085)
Ettore Di Giacinto committed
October 5, 2024
E
feat(shutdown): allow force shutdown of backends (#3733)
Ettore Di Giacinto committed
October 2, 2024
E
fix(initializer): correctly reap dangling processes (#3717)
Ettore Di Giacinto committed
E
feat: track internally started models by ID (#3693)
Ettore Di Giacinto committed
September 26, 2024
E
chore(refactor): track grpcProcess in the model structure (#3663)
Ettore Di Giacinto committed
September 25, 2024
E
feat(api): list loaded models in `/system` (#3661)
Ettore Di Giacinto committed
September 17, 2024
E
chore(refactor): drop duplicated shutdown logics (#3589)
Ettore Di Giacinto committed
E
fix(shutdown): do not shutdown immediately busy backends (#3543)
Ettore Di Giacinto committed
August 30, 2024
E
chore(model-loader): increase test coverage of model loader (#3433)
Ettore Di Giacinto committed
August 25, 2024
E
fix(model-loading): keep track of open GRPC Clients (#3377)
Ettore Di Giacinto committed
July 18, 2024
E
fix: do not list txt files as potential models (#2910)
Ettore Di Giacinto committed
July 11, 2024
E
feat(webui): show also models without a config in the welcome page (#2772)
Ettore Di Giacinto committed
July 10, 2024
E
feat(model-list): be consistent, skip known files from listing (#2760)
Ettore Di Giacinto committed
June 23, 2024
S
chore: fix go.mod module (#2635)
Sertaç Özercan committed
April 29, 2024
April 28, 2024
E
feat(gallery): support model deletion (#2173)
Ettore Di Giacinto committed
April 19, 2024
E
refactor(template): isolate and add tests (#2069)
Ettore Di Giacinto committed
April 18, 2024
E
feat(functions): support models with no grammar, add tests (#2068)
Ettore Di Giacinto committed
March 23, 2024
E
fix(watchdog): use ShutdownModel instead of StopModel (#1882)
Ettore Di Giacinto committed
March 21, 2024
E
feat(functions/aio): all-in-one images, function template enhancements (#1862)
Ettore Di Giacinto committed
February 17, 2024
E
feat(tools): support Tool calls in the API (#1715)
Ettore Di Giacinto committed
January 23, 2024
C
feat(grpc): backend SPI pluggable in embedding mode (#1621)
coyzeng committed
January 7, 2024
E
feat: more embedded models, coqui fixes, add model usage and description (#1556)
Ettore Di Giacinto committed
January 5, 2024
E
Revert "[Refactor]: Core/API Split" (#1550)
Ettore Di Giacinto committed
D
[Refactor]: Core/API Split (#1506)
Dave committed
December 18, 2023
E
feat: inline templates and accept URLs in models (#1452)
Ettore Di Giacinto committed
November 26, 2023
E
feat: initial watchdog implementation (#1341)
Ettore Di Giacinto committed
November 16, 2023
E
feat: queue up requests if not running parallel requests (#1296)
Ettore Di Giacinto committed