90ca84172c
* Fix embeddings memory corruption The patch was leading to a buffer overrun corruption. Once removed though, parallism in server.cpp lead to hitting an assert due to slot/seq IDs being >= token count. To work around this, only use slot 0 for embeddings. * Fix embed integration test assumption The token eval count has changed with recent llama.cpp bumps (0.3.5+) |
||
|---|---|---|
| .. | ||
| 01-load-progress.diff | ||
| 02-clip-log.diff | ||
| 03-load_exception.diff | ||
| 04-metal.diff | ||
| 05-default-pretokenizer.diff | ||
| 06-embeddings.diff | ||
| 07-clip-unicode.diff | ||
| 09-lora.diff | ||
| 11-phi3-sliding-window.diff | ||