matt/ollama37
1
0
Fork 0
mirror of https://github.com/dogkeeper886/ollama37.git synced 2025-12-17 19:27:00 +00:00
Code Issues Packages Projects Releases Wiki Activity

image processing for llama3.2 (#6963)

Browse Source 
Co-authored-by: jmorganca <jmorganca@gmail.com>
Co-authored-by: Michael Yang <mxyng@pm.me>
Co-authored-by: Jesse Gross <jesse@ollama.com>
This commit is contained in:
Patrick Devine
2024-10-18 16:12:35 -07:00
committed by GitHub
parent bf4018b9ec
commit c7cb0f0602
35 changed files with 3851 additions and 203 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
llama/ggml-cuda.cu vendored
View File

@@ -2296,6 +2296,9 @@ static bool ggml_cuda_compute_forward(ggml_backend_cuda_context & ctx, struct gg
case GGML_OP_PAD:
ggml_cuda_op_pad(ctx, dst);
break;
case GGML_OP_UNPAD:
ggml_cuda_op_unpad(ctx, dst);
break;
case GGML_OP_ARANGE:
ggml_cuda_op_arange(ctx, dst);
break;
@@ -3018,6 +3021,7 @@ GGML_CALL static bool ggml_backend_cuda_supports_op(ggml_backend_t backend, cons
case GGML_OP_GROUP_NORM:
case GGML_OP_UPSCALE:
case GGML_OP_PAD:
case GGML_OP_UNPAD:
case GGML_OP_ARANGE:
case GGML_OP_TIMESTEP_EMBEDDING:
case GGML_OP_LEAKY_RELU: