| Age | Commit message (Expand) | Author |
|---|---|---|
| 2025-04-07 | Add copyright notices (#317) | Kawrakow |
| 2025-03-18 | Make Q8_0 KV cache work with mla=2,fa on CUDA (#264) | Kawrakow |
| 2025-03-18 | FlashMLA-2: reduce compute buffer size (CUDA and CPU) (#260) | Kawrakow |
| 2025-03-01 | Reduce size of compute buffers (#237) | 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 |