Peter Steinberger 97b13b1735 fix(llama-cpp): preserve managed local embedding batch capacity (#128721) ...

Preserve the contributor fix from #127288 and its original Git author. Thanks @cantoblanco for the original issue and pull request.

Co-authored-by: Alex <alex@example.com>

2026-08-24 05:46:59 -07:00

..

external-server

refactor(providers): return prepared dynamic models directly (#126574)

2026-08-21 11:40:52 -07:00

auth-config.ts

refactor(llama-cpp): use one provider for managed and existing servers (#126434)

2026-08-19 13:57:33 -07:00

defaults.ts

feat(llama-cpp): raise default context size to 64K (#123701)

2026-08-14 08:26:41 -07:00

embedding-provider.ts

fix(llama-cpp): preserve managed local embedding batch capacity (#128721)

2026-08-24 05:46:59 -07:00

llama-server-assets.ts

chore: refresh dependencies after seven-day cooldown (#128414)

2026-08-24 03:01:54 -07:00

llama-server-install.test.ts

chore: refresh dependencies after seven-day cooldown (#128414)

2026-08-24 03:01:54 -07:00

llama-server-install.ts

chore: refresh dependencies after seven-day cooldown (#128414)

2026-08-24 03:01:54 -07:00

managed-provider-config.ts

fix(doctor): report missing managed local embedding setup (#123575)

2026-08-15 20:15:06 -06:00

managed-provider.ts

refactor(providers): return prepared dynamic models directly (#126574)

2026-08-21 11:40:52 -07:00

managed-server.test.ts

fix(llama-cpp): preserve managed local embedding batch capacity (#128721)

2026-08-24 05:46:59 -07:00

managed-server.ts

fix(llama-cpp): preserve managed local embedding batch capacity (#128721)

2026-08-24 05:46:59 -07:00

setup.test.ts

fix(llama-cpp): make endpoint auth transitions reproducible (#126498)

2026-08-19 18:37:28 -07:00

setup.ts

fix(llama-cpp): preserve managed local embedding batch capacity (#128721)

2026-08-24 05:46:59 -07:00