tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-07-02 14:35:42 +00:00
Code Issues Packages Projects Releases Wiki Activity

ggml : refactor rope norm/neox (#7634)

Browse Source 
* ggml : unify rope norm/neox (CPU)

* ggml : fix compile warning

* ggml : remove GLM rope mode

ggml-ci

* metal : better rope implementation

ggml-ci

* cuda : better rope implementation

ggml-ci

* naming : n_orig_ctx -> n_ctx_orig

ggml-ci

* dev : add reminders to update backends

ggml-ci

* vulkan : fix ggml_rope_ext() usage

* cuda : fix array size + indents

ggml-ci
This commit is contained in:
Georgi Gerganov
2024-06-05 11:29:20 +03:00
committed by GitHub
parent 9973e81c5c
commit 2b3389677a
19 changed files with 485 additions and 732 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
examples/train-text-from-scratch/train-text-from-scratch.cpp
View File

@ -302,7 +302,7 @@ static struct ggml_tensor * llama_build_train_graphs(
const int rope_mode = 0;
return ggml_rope_ext(
ctx, t, KQ_pos, nullptr, n_rot, rope_mode, n_ctx, 0, rope_freq_base, rope_freq_scale, 0.0f, 1.0f, 0.0f, 0.0f
ctx, t, KQ_pos, nullptr, n_rot, rope_mode, n_ctx, rope_freq_base, rope_freq_scale, 0.0f, 1.0f, 0.0f, 0.0f
);
};