tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-08-04 16:23:49 -04:00
Code Issues Packages Projects Releases Wiki Activity

kv-cache : use ggml_set_rows (#14285)

Browse Source 
* kv-cache : use ggml_set_rows

ggml-ci

* graph : separate k and v indices

ggml-ci

* cont : remove redundant ifs

ggml-ci

* kv-cache : improve find_slot impl

* kv-cache : bounds-check when accessing slot_info indices

* kv-cache : add comments

ggml-ci

* ggml : add TODOs for adding GGML_OP_SET_ROWS support in the backends

ggml-ci
This commit is contained in:
Georgi Gerganov
2025-07-03 10:53:35 +03:00
committed by GitHub
parent 9067487c44
commit a70c8a0c4b
13 changed files with 451 additions and 143 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
ggml/src/ggml-opencl/ggml-opencl.cpp
View File

@@ -2222,6 +2222,12 @@ static bool ggml_opencl_supports_op(ggml_backend_dev_t dev, const struct ggml_te
default:
return false;
}
case GGML_OP_SET_ROWS:
{
// TODO: add support
// ref: https://github.com/ggml-org/llama.cpp/pull/14274
return false;
} break;
case GGML_OP_CPY:
case GGML_OP_DUP:
case GGML_OP_CONT: