nhcarrigan/chronara
9
0
Fork 0
generated from nhcarrigan/template
Code Issues 1 Pull Requests 1 Actions Releases 1 Activity

feat: we successfully have the installer working for windows!
Security Scan and Upload / Security & DefectDojo Upload (pull_request) Successful in 2m25s
Details
CI / Lint & Test (pull_request) Failing after 6m21s
Details
CI / Build Linux (pull_request) Has been skipped
Details
CI / Build Windows (cross-compile) (pull_request) Has been skipped
Details

Browse Source 
Models are downloaded at runtime instead of build.
This commit is contained in:
Naomi Carrigan
2026-01-28 17:15:13 -08:00
parent 3c8a46e5a6
commit 74c334c939
684 changed files with 431984 additions and 192 deletions
Download Patch File Download Diff File Expand all files Collapse all files
patches/llama-cpp-sys-2/llama.cpp/ggml/src/ggml-cuda/binbcast.cuh
+11
View File
@@ -0,0 +1,11 @@
#include "common.cuh"
void ggml_cuda_op_repeat(ggml_backend_cuda_context & ctx, ggml_tensor * dst);
void ggml_cuda_op_add(ggml_backend_cuda_context & ctx, ggml_tensor * dst);
void ggml_cuda_op_sub(ggml_backend_cuda_context & ctx, ggml_tensor * dst);
void ggml_cuda_op_mul(ggml_backend_cuda_context & ctx, ggml_tensor * dst);
void ggml_cuda_op_div(ggml_backend_cuda_context & ctx, ggml_tensor * dst);
void ggml_cuda_op_repeat_back(ggml_backend_cuda_context & ctx, ggml_tensor * dst);
void ggml_cuda_op_fused_add(ggml_backend_cuda_context & ctx, ggml_tensor * dst, int n_fuse);