mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2025-11-12 10:47:01 +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:
@@ -3427,7 +3427,7 @@ static bool ggml_backend_cuda_device_supports_op(ggml_backend_dev_t dev, const g
|
||||
op->type == GGML_TYPE_Q4_0 || op->type == GGML_TYPE_Q4_1 || op->type == GGML_TYPE_Q5_0 ||
|
||||
op->type == GGML_TYPE_Q5_1 || op->type == GGML_TYPE_Q8_0 || op->type == GGML_TYPE_IQ4_NL) &&
|
||||
op->src[0]->type == GGML_TYPE_F32 &&
|
||||
op->src[1]->type == GGML_TYPE_I64;
|
||||
(op->src[1]->type == GGML_TYPE_I64 || op->src[1]->type == GGML_TYPE_I32);
|
||||
} break;
|
||||
case GGML_OP_CPY:
|
||||
{
|
||||
|
||||
Reference in New Issue
Block a user