ikawrakow/ik_llama.cpp
1
0
Fork 0
mirror of https://github.com/ikawrakow/ik_llama.cpp.git synced 2026-04-24 16:39:45 +00:00
Code Issues Packages Projects Releases Wiki Activity

move thing fix

Browse Source
This commit is contained in:
Saood Karim
2025-06-18 12:36:41 -05:00
parent ed17aa1015
commit 829a4d7177
1 changed files with 0 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
README.md
View File

@@ -64,7 +64,6 @@ Cuda implementations: `IQ4_KS_R4` and `IQ5_KS_R4` [PR 493](https://github.com/i
* May 13 2025: Better CPU FA performance for DeepSeek-Lite. [PR 410](https://github.com/ikawrakow/ik_llama.cpp/pull/410)
* May 11 2025: Slightly faster flash attention for DeepSeek models on CUDA, along with extending compatibility to Touring or newer GPUs. [PR 408](https://github.com/ikawrakow/ik_llama.cpp/pull/408)
* May 7 2025: Faster TG for DeepSeek models with GPU or hybrid GPU/CPU inference. [PR 386](https://github.com/ikawrakow/ik_llama.cpp/pull/386). Caveat: Ampere or newer Nvidia GPU required
* May 4 2025: Significant token generation performance improvement on CUDA with Flash Attention for GQA models. For details and benchmarks. [PR 370](https://github.com/ikawrakow/ik_llama.cpp/pull/370)
* April 17 2025: Better CPU Flash Attention token generation performance. [PR 332](https://github.com/ikawrakow/ik_llama.cpp/pull/332)
* April 3 2025: Much faster MoE implementation on Metal. [PR 307](https://github.com/ikawrakow/ik_llama.cpp/pull/307)