highperfocused/ollama
1
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2025-11-11 07:07:54 +01:00
Code Issues Packages Projects Releases Wiki Activity
Files
pdevine/parser-tidy
ollama/llm/memory.go
Jesse Gross 71cb86af3e llm: Remove unneeded warning with flash attention enabled 
If flash attention is enabled without KV cache quanitization, we will
currently always get this warning:
level=WARN source=server.go:226 msg="kv cache type not supported by model" type=""
2025-09-10 16:40:45 -07:00

15 KiB
Raw Permalink Blame History

View Raw
Reference in New Issue View Git Blame Copy Permalink