Tags: InferenceNexus/llama-box
Tags
refactor: tool calling Signed-off-by: thxCode <[email protected]>
chore: bump llama.cpp Signed-off-by: thxCode <[email protected]>
refactor: metric prefix Signed-off-by: thxCode <[email protected]>
refactor: metal patch Signed-off-by: thxCode <[email protected]>
fix: embeddings/rerank processing Signed-off-by: thxCode <[email protected]>
ci: adjust cuda build Signed-off-by: thxCode <[email protected]>
fix: failed decoding llava 1.6 Signed-off-by: thxCode <[email protected]>
refactor: support sd no tiling vae Signed-off-by: thxCode <[email protected]>
PreviousNext