An embedding model is served for embedding, with many slots

ctl model serve served one as a chat model: no --embedding, four slots, a
512-token batch, embeddings unset, and a chat smoke test it could not
pass. A GGUF that pools (<arch>.pooling_type), or --embeddings, gets
--embedding, 32 slots of 1024 tokens unless sized otherwise, a batch that
holds a whole passage, the embeddings capability, and one vector asked for
as its smoke test (canaries and updates too). An import of a hundred
thousand chunks had gone at the pace of four slots with the card a third
busy.

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
This commit is contained in:
Ilker ManapandClaude Opus 5.5 committed 2026-10-14 09:19:57 +02:00
1 parent f5eb6963af
commit efffdb66b7
8 files changed
+142 -6

No files matched your search

+6
View File
@@ -36,6 +36,12 @@ APIs change between minors without a deprecation period.
### Fixed
- `llmgw ctl model serve` served an embedding model as a chat model: no
`--embedding`, four slots, a 512-token batch, `embeddings` unset and a
"say hello" smoke test it could not pass. A model whose GGUF says it
pools (or `--embeddings`) is served for embedding: 32 slots of 1024
tokens unless sized otherwise, a batch that holds a whole passage, and
one vector asked for as its smoke test.
- `llmgw ctl upgrade` checks every node's version once the waves are done
and fails naming any not on the release, and says when the control plane
has no nodes registered; `llmgw upgrade` on a control plane says how many