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

..

httpapi

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

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

inproc

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

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

prompts

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

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

capability.go

feat: localai assistant chat modality (#9602)

2026-04-28 19:29:27 +02:00

client.go

feat(vram): per-node VRAM allocation budget (LOCALAI_VRAM_BUDGET) (#10833)

2026-07-15 09:58:45 +02:00

coverage_test.go

feat(vram): per-node VRAM allocation budget (LOCALAI_VRAM_BUDGET) (#10833)

2026-07-15 09:58:45 +02:00

doc.go

feat: localai assistant chat modality (#9602)

2026-04-28 19:29:27 +02:00

dto_test.go

feat: localai assistant chat modality (#9602)

2026-04-28 19:29:27 +02:00

dto.go

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

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

errors.go

feat: localai assistant chat modality (#9602)

2026-04-28 19:29:27 +02:00

fakes_test.go

feat(vram): per-node VRAM allocation budget (LOCALAI_VRAM_BUDGET) (#10833)

2026-07-15 09:58:45 +02:00

parity_test.go

feat: localai assistant chat modality (#9602)

2026-04-28 19:29:27 +02:00

prompts_test.go

feat: localai assistant chat modality (#9602)

2026-04-28 19:29:27 +02:00

prompts.go

feat: localai assistant chat modality (#9602)

2026-04-28 19:29:27 +02:00

server_test.go

feat(vram): per-node VRAM allocation budget (LOCALAI_VRAM_BUDGET) (#10833)

2026-07-15 09:58:45 +02:00

server.go

[voice] feat: add managed voice cloning profiles (#10799)

2026-07-13 09:54:46 +02:00

tools_aliases.go

feat(models): model aliases - redirect a model name to another configured model (#10414)

2026-06-20 22:38:42 +02:00

tools_backends.go

feat: localai assistant chat modality (#9602)

2026-04-28 19:29:27 +02:00

tools_branding.go

feat(branding): admin-configurable instance name, tagline, and assets (#9635)

2026-05-02 15:51:36 +02:00

tools_config.go

feat: localai assistant chat modality (#9602)

2026-04-28 19:29:27 +02:00

tools_middleware.go

feat(pii): NER tier engine — privacy-filter.cpp backend + NER-centric PII filter (#10360)

2026-06-18 11:45:22 +01:00

tools_models.go

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

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

tools_pii.go

feat(pii): NER tier engine — privacy-filter.cpp backend + NER-centric PII filter (#10360)

2026-06-18 11:45:22 +01:00

tools_state.go

feat: localai assistant chat modality (#9602)

2026-04-28 19:29:27 +02:00

tools_system.go

feat(vram): per-node VRAM allocation budget (LOCALAI_VRAM_BUDGET) (#10833)

2026-07-15 09:58:45 +02:00

tools_usage.go

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

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

tools_voice_profiles.go

[voice] feat: add managed voice cloning profiles (#10799)

2026-07-13 09:54:46 +02:00

tools.go

feat(vram): per-node VRAM allocation budget (LOCALAI_VRAM_BUDGET) (#10833)

2026-07-15 09:58:45 +02:00