frank-medium: pass --mmproj explicitly; this build has no autoload
The 36:29/327680/vision deploy came up healthy and text-only: image requests answered 500 'image input is not supported - hint: ... provide the mmproj' with no mmproj line in the load log, so llama-server fb27a525 does not autoload mmproj*.gguf from the model directory. Name the file, the way frank-small's serve script already does, and pin the flag in the seam.
This commit is contained in:
1 parent
d95f55b822
commit
ddf69c4107
2 files changed
+9
-3
No files matched your search
@@ -230,7 +230,8 @@ print('draft-model wiring ok')
|
||||
grep -q '^NO_MMPROJ=0$' "$ENV_FILE"
|
||||
grep -q '^MM_PROJ_FILE=mmproj-BF16.gguf$' "$ENV_FILE"
|
||||
# The serve script refuses to start without the projector when vision is
|
||||
# on, so a missing file is a deploy error, not a silent text-only server.
|
||||
# Explicit flag, not autoload: this build starts text-only without it.
|
||||
grep -q -- '--mmproj "$MM_PROJ"' "$SERVE"
|
||||
grep -q 'vision is enabled but the projector is missing' "$SERVE"
|
||||
# And the download script fetches and byte-verifies it.
|
||||
grep -q '^MM_PROJ_SIZE=931145888$' "$FETCH"
|
||||
|
||||
Reference in new issue
Block a user