highperfocused/ollama
1
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2025-11-11 18:27:06 +01:00
Code Issues Packages Projects Releases Wiki Activity
Files
e093db92c4731b0cada767c7d5877c20d5f61dcf
ollama/ml/backend/ggml
History
Jesse Gross 4100ed7bdd 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.
2025-03-07 18:43:39 -08:00
..
ggml
model: load non-repeated tensors into multiple backends
2025-03-07 14:08:21 -08:00
ggml.go
ml: Add support for quantized KV cache
2025-03-07 18:43:39 -08:00