mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2025-11-09 10:17:06 +00:00
ggml : implement set_rows with i32 index (#16159)
* implement set_rows with i32 index * template fix * test quantized path warnings-- * Apply suggestions from code review Co-authored-by: Georgi Gerganov <ggerganov@gmail.com> * forgotten name change * deduplicate cuda/sycl and test-fix * indent++ * vulkan: support set_rows with i32 index type (#16162) * disable i32 index for webgpu for now --------- Co-authored-by: Georgi Gerganov <ggerganov@gmail.com> Co-authored-by: Jeff Bolz <jbolz@nvidia.com>
This commit is contained in:
@@ -1310,7 +1310,7 @@ static bool ggml_backend_webgpu_device_supports_op(ggml_backend_dev_t dev, const
|
||||
break;
|
||||
case GGML_OP_CPY:
|
||||
case GGML_OP_SET_ROWS:
|
||||
supports_op = (op->type == GGML_TYPE_F16 && op->src[0]->type == GGML_TYPE_F32);
|
||||
supports_op = (op->type == GGML_TYPE_F16 && op->src[0]->type == GGML_TYPE_F32 && op->src[1]->type == GGML_TYPE_I64);
|
||||
break;
|
||||
case GGML_OP_GET_ROWS:
|
||||
if (op->src[0]->type == GGML_TYPE_F32 || op->src[0]->type == GGML_TYPE_F16 ||
|
||||
|
||||
Reference in New Issue
Block a user