diff options
| author | Kawrakow <iwankawrakow@gmail.com> | 2025-05-09 11:16:36 +0300 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2025-05-09 11:16:36 +0300 |
| commit | e5a4a3ce78ce96b6822dcd6138a98c4d237ecc9b (patch) | |
| tree | 57c1d245bc24036c1a139b1a2c6d6da1bbcdb8a3 | |
| parent | 8777fc4855dd1551c20a84cb266f75fa49e9b0e8 (diff) | |
Update README.md
@saood06 Thanks!
| -rw-r--r-- | README.md | 2 |
1 files changed, 1 insertions, 1 deletions
@@ -14,7 +14,7 @@ This repository is a fork of [llama.cpp](https://github.com/ggerganov/llama.cpp) ## Latest News -* May 9 2025: Support for LlaMA-3-Nmotron models added, see [PR 377](https://github.com/ikawrakow/ik_llama.cpp/pull/377) +* May 9 2025: Support for LlaMA-3-Nemotron models added, see [PR 377](https://github.com/ikawrakow/ik_llama.cpp/pull/377) * May 7 2025: 🚀 Faster TG for DeepSeek models with GPU or hybrid GPU/CPU inference. See [PR 386](https://github.com/ikawrakow/ik_llama.cpp/pull/386) for details. 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 see [PR #370](https://github.com/ikawrakow/ik_llama.cpp/pull/370) * April 29 2025: Qwen3 support added |