| Age | Commit message (Expand) | Author |
|---|---|---|
| 2024-10-22 | Enable q6_0 for flash attention (#101) | Kawrakow |
| 2024-10-21 | Enable IQ4_NL for KV-cache in token generation using Flash Attention (#99) | Kawrakow |
| 2024-09-09 | Add CUDA support for IQ1_TN (#45) | Kawrakow |
| 2024-08-27 | Faster Gemma2 (#27) | Kawrakow |
| 2024-08-12 | Merge mainline - Aug 12 2024 (#17) | Kawrakow |
| 2024-07-27 | Merge mainline llama.cpp (#3) | Kawrakow |
 |
index : ik_llama.cpp.git | |
| Unnamed repository; edit this file 'description' to name the repository. |
| summaryrefslogtreecommitdiff |