LocalAI/pkg
Ettore Di Giacinto 031a36c995
feat: inferencing default, automatic tool parsing fallback and wire min_p (#9092)
* feat: wire min_p

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* feat: inferencing defaults

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* chore(refactor): re-use iterative parser

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* chore: generate automatically inference defaults from unsloth

Instead of trying to re-invent the wheel and maintain here the inference
defaults, prefer to consume unsloth ones, and contribute there as
necessary.

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* chore: apply defaults also to models installed via gallery

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* chore: be consistent and apply fallback to all endpoint

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

---------

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2026-03-22 00:57:15 +01:00
..
audio feat(realtime): WebRTC support (#8790) 2026-03-13 21:37:15 +01:00
concurrency chore: update jobresult_test.go (#4124) 2024-11-12 08:52:18 +01:00
downloader chore(size): display size of HF models and allow to specify it from the gallery (#8907) 2026-03-09 17:38:14 +01:00
format feat(api): Add transcribe response format request parameter & adjust STT backends (#8318) 2026-02-01 17:33:17 +01:00
functions feat: inferencing default, automatic tool parsing fallback and wire min_p (#9092) 2026-03-22 00:57:15 +01:00
grpc feat(quantization): add quantization backend (#9096) 2026-03-22 00:56:34 +01:00
huggingface-api feat(hf-api): return files in nested directories (#7396) 2025-11-30 09:06:54 +01:00
langchain Remove HuggingFace backend support (#8971) 2026-03-13 01:09:30 +01:00
model feat(ui): Per model backend logs and various fixes (#9028) 2026-03-18 08:31:26 +01:00
oci feat(ui): allow to cancel ops (#7264) 2025-11-13 18:41:47 +01:00
reasoning chore: refactor endpoints to use same inferencing path, add automatic retrial mechanism in case of errors (#9029) 2026-03-16 21:31:02 +01:00
signals chore: update cogito and simplify MCP logics (#6413) 2025-10-09 12:36:45 +02:00
sound feat(realtime): WebRTC support (#8790) 2026-03-13 21:37:15 +01:00
store chore: fix go.mod module (#2635) 2024-06-23 08:24:36 +00:00
system fix: gate CUDA directory checks on GPU vendor to prevent false CUDA detection (#8942) 2026-03-12 07:53:39 +01:00
utils Add sample_rate support to TTS API via post-processing resampling (#8650) 2026-02-25 16:36:27 +01:00
vram chore(size): display size of HF models and allow to specify it from the gallery (#8907) 2026-03-09 17:38:14 +01:00
xio feat(ui): allow to cancel ops (#7264) 2025-11-13 18:41:47 +01:00
xsync chore: fix go.mod module (#2635) 2024-06-23 08:24:36 +00:00
xsysinfo fix: drop gguf VRAM estimation (now redundant) (#8325) 2026-02-01 17:33:28 +01:00