ollama/llm/patches
Daniel Hiltgen 90ca84172c
Fix embeddings memory corruption (#6467)
* 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+)
2024-08-22 14:51:42 -07:00
..
01-load-progress.diff update llama.cpp submodule to d7fd29f (#5475) 2024-07-05 13:25:58 -04:00
02-clip-log.diff Fix clip log import 2024-04-26 09:43:46 -07:00
03-load_exception.diff update llama.cpp submodule to d7fd29f (#5475) 2024-07-05 13:25:58 -04:00
04-metal.diff update llama.cpp submodule to d7fd29f (#5475) 2024-07-05 13:25:58 -04:00
05-default-pretokenizer.diff update llama.cpp submodule to 6eeaeba1 (#6039) 2024-07-29 13:20:26 -07:00
06-embeddings.diff Update llama.cpp submodule commit to d94c6e0c (#5805) 2024-07-22 12:42:00 -04:00
07-clip-unicode.diff Update llama.cpp submodule commit to d94c6e0c (#5805) 2024-07-22 12:42:00 -04:00
09-lora.diff update llama.cpp submodule to 1e6f6554 (#6208) 2024-08-06 15:11:45 -04:00
11-phi3-sliding-window.diff patches: phi3 default sliding window attention 2024-07-31 14:58:34 -07:00