LocalAI [bot] c500461c69 feat(config): default prompt_cache_all to true (#9951) ...

Upstream llama.cpp defaults `cache_prompt = true` (common/common.h),
but `parse_options` in the grpc-server backend unconditionally forwards
the proto `PromptCacheAll` field, so any model that didn't set
`prompt_cache_all: true` in its YAML was getting `cache_prompt=false` —
silently overriding llama.cpp's own default. With `kv_unified` and
`cache_idle_slots` already on by default, this was the last piece
preventing the per-request prompt cache from being usable out of the
box.

Make `PromptCacheAll` tristate (`*bool`), default it to `true` in
`SetDefaults`, and dereference at the proto boundary. Users can still
opt out with an explicit `prompt_cache_all: false`. Same pattern as
`MMap`, `MMlock`, `Reranking`, etc.

Co-authored-by: Ettore Di Giacinto <mudler@localai.io>
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

2026-05-22 22:06:22 +02:00

..

application

fix(traces): cap captured body size to keep admin Traces UI responsive (#9946)

2026-05-22 15:29:24 +02:00

backend

feat(config): default prompt_cache_all to true (#9951)

2026-05-22 22:06:22 +02:00

cli

fix(traces): cap captured body size to keep admin Traces UI responsive (#9946)

2026-05-22 15:29:24 +02:00

clients

feat: add distributed mode (#9124)

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

config

feat(config): default prompt_cache_all to true (#9951)

2026-05-22 22:06:22 +02:00

dependencies_manager

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

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

explorer

chore: Security hardening (#9719)

2026-05-08 16:25:45 +02:00

gallery

feat(gallery): verify backend OCI images with keyless cosign (#9823)

2026-05-18 08:02:20 +02:00

http

fix(react-ui): unify backend-logs entry point for distributed mode (#9949)

2026-05-22 22:00:08 +02:00

p2p

feat: add distributed mode (#9124)

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

schema

fix(ollama): accept float-encoded integer options (fixes #9837) (#9849)

2026-05-16 18:38:19 +02:00

services

fix(nodes): make per-node backend install async via gallery job queue (#9928)

2026-05-21 22:25:53 +02:00

startup

feat(gallery): verify backend OCI images with keyless cosign (#9823)

2026-05-18 08:02:20 +02:00

templates

fix(vision): propagate mtmd media marker from backend via ModelMetadata (#9412)

2026-04-18 20:30:13 +02:00

trace

feat: add LocalVQE backend and audio transformations UI (#9640)

2026-05-04 22:07:11 +02:00