highperfocused/ollama
1
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2025-03-19 22:32:15 +01:00
Code Issues Packages Projects Releases Wiki Activity
ollama/ml
History
Jesse Gross 5beede47d9 ml: Add support for quantized KV cache 
Similar to the llama engine, quantizing the KV cache requires
flash attention to be enabled through the Ollama server.
2025-02-27 17:09:16 -08:00
..
backend
ml: Add support for quantized KV cache
2025-02-27 17:09:16 -08:00
nn
attention: Remove unnecessary contiguous operations
2025-02-27 17:06:41 -08:00
backend.go
ml: Add support for quantized KV cache
2025-02-27 17:09:16 -08:00