github/gpt4all
1
0
Fork 0
mirror of https://github.com/nomic-ai/gpt4all.git synced 2025-09-09 04:20:42 +00:00
Code Issues Packages Projects Releases Wiki Activity

backend: update to latest commit of llama.cpp Vulkan PR

Browse Source 
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
This commit is contained in:
Jared Van Bortel
2024-01-25 16:58:46 -05:00
committed by AT
parent 29d2c936d1
commit 38c61493d2
9 changed files with 85 additions and 125 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
gpt4all-backend/gptj.cpp
View File

@@ -414,11 +414,7 @@ bool gptj_eval(
struct ggml_tensor * KQ = ggml_mul_mat(ctx0, K, Q);
// KQ_scaled = KQ / sqrt(n_embd/n_head)
struct ggml_tensor * KQ_scaled =
ggml_scale(ctx0,
KQ,
ggml_new_f32(ctx0, 1.0f/sqrt(float(n_embd)/n_head))
);
struct ggml_tensor * KQ_scaled = ggml_scale(ctx0, KQ, 1.0f/sqrt(float(n_embd)/n_head));
// KQ_masked = mask_past(KQ_scaled)
struct ggml_tensor * KQ_masked = ggml_diag_mask_inf(ctx0, KQ_scaled, n_past);