Ettore Di Giacinto c1d2947616 fix(cli,mcp): describe variant auto-selection as preference before size ...

The CLI flag help and the install_model tool schema both still said
auto-selection takes the largest build that runs. Ranking now puts engine
preference ahead of size, so on NVIDIA a vLLM build wins over a larger
llama.cpp one. An assistant reading the old schema would tell users the
wrong thing.

Assisted-by: Claude:claude-opus-4-8
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

2026-07-19 22:07:04 +00:00

..

application

fix(p2p): serialize access to p2pCtx/p2pCancel (#10839) (#10861)

2026-07-17 09:02:05 +02:00

backend

fix(model-artifacts): load single-file HF snapshots from the file, not the directory (#10909)

2026-07-17 22:42:50 +00:00

cli

fix(cli,mcp): describe variant auto-selection as preference before size

2026-07-19 22:07:04 +00:00

clients

security(http): refuse redirects on outbound clients via hardened pkg/httpclient (#10087)

2026-05-30 12:04:10 +02:00

config

fix(model-artifacts): gate inferred artifact materialization by backend (#10910)

2026-07-17 23:26:23 +00:00

dependencies_manager

feat(ui): move to React for frontend (#8772)

2026-03-05 21:47:12 +01:00

explorer

feat(middleware): Model routing, PII filtering, Cloud model proxies (#9802)

2026-05-25 09:28:27 +02:00

gallery

fix(gallery): rank variants by engine name, not backend build tag

2026-07-19 21:59:23 +00:00

http

feat(ui): show the collapsed model listing by default

2026-07-19 20:49:17 +00:00

p2p

feat: add distributed mode (#9124)

2026-03-30 00:47:27 +02:00

schema

feat(gallery): drop the redundant variant min_memory field

2026-07-18 23:18:12 +00:00

services

fix(gallery): rank the entry's own build against its variants

2026-07-18 23:49:14 +00:00

startup

feat(gallery): expose model variants for selection over API, CLI and MCP

2026-07-18 23:06:17 +00:00

templates

fix(openresponses): populate Content and accept bare {role,content} items (#10039) (#10040)

2026-05-28 07:21:48 +00:00

trace

feat(realtime): eager blocking pipeline warm-up + /backend/load API (#10662)

2026-07-03 18:00:37 +02:00