github/gpt4all
1
0
Fork 0
mirror of https://github.com/nomic-ai/gpt4all.git synced 2025-06-21 13:10:35 +00:00
Code Issues Packages Projects Releases Wiki Activity

Add q8_0 kernels to kompute shaders and bump to latest llama/gguf.

Browse Source
This commit is contained in:
Adam Treat 2023-10-05 10:52:58 -04:00
parent 1534df3e9f
commit f605a5b686
2 changed files with 3 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
gpt4all-backend/llama.cpp-mainline

@ -1 +1 @@
Subproject commit 7f8f62880cf3242cc0d3b54465bed4e2d59e4774 Subproject commit 2b7b3f37f9d0193943c3d31e3e617bc6351838c8

2
gpt4all-backend/llama.cpp.cmake
View File

@ -239,6 +239,7 @@ if (LLAMA_KOMPUTE)
kompute/op_rmsnorm.comp kompute/op_rmsnorm.comp
kompute/op_diagmask.comp kompute/op_diagmask.comp
kompute/op_mul_mat_f16.comp kompute/op_mul_mat_f16.comp
kompute/op_mul_mat_q8_0.comp
kompute/op_mul_mat_q4_0.comp kompute/op_mul_mat_q4_0.comp
kompute/op_mul_mat_q4_1.comp kompute/op_mul_mat_q4_1.comp
kompute/op_mul_mat_q6_k.comp kompute/op_mul_mat_q6_k.comp
@ -268,6 +269,7 @@ if (LLAMA_KOMPUTE)
shaderop_rmsnorm.h shaderop_rmsnorm.h
shaderop_diagmask.h shaderop_diagmask.h
shaderop_mul_mat_f16.h shaderop_mul_mat_f16.h
shaderop_mul_mat_q8_0.h
shaderop_mul_mat_q4_0.h shaderop_mul_mat_q4_0.h
shaderop_mul_mat_q4_1.h shaderop_mul_mat_q4_1.h
shaderop_mul_mat_q6_k.h shaderop_mul_mat_q6_k.h