vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

RoPE: fix back, CUDA support for back + noncont. (#11240)

Browse source 
* RoPE: fix back, CUDA support for back + noncont.

* fix comments reg. non-cont. RoPE support [no-ci]
This commit is contained in:
Johannes Gäßler 2025-01-15 12:51:37 +01:00 • committed by GitHub
parent 0ccd7f3eb2
commit 432df2d5f9
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
9 changed files with 269 additions and 258 deletions
Download patch file Download diff file Expand all files Collapse all files

1
ggml/src/ggml-cpu/ggml-cpu.c
View file

@ -13668,6 +13668,7 @@ struct ggml_cplan ggml_graph_plan(
} break;
case GGML_OP_SOFT_MAX:
case GGML_OP_ROPE:
case GGML_OP_ROPE_BACK:
{
cur = ggml_type_size(GGML_TYPE_F32) * node->ne[0] * n_tasks;
} break;

2
ggml/src/ggml-cpu/ggml-cpu.cpp
View file

@ -403,8 +403,6 @@ static bool ggml_backend_cpu_device_supports_op(ggml_backend_dev_t dev, const st
op->type != GGML_TYPE_IQ1_M; // missing type_traits.from_float
case GGML_OP_MUL_MAT:
return src1->type == GGML_TYPE_F32 || src1->type == ggml_get_type_traits_cpu(src0->type)->vec_dot_type;
case GGML_OP_ROPE_BACK:
return op->src[2] == NULL && (op->op_params[2] & 4) == 0;
case GGML_OP_IM2COL_BACK:
return src0->type == GGML_TYPE_F32 && src1->type == GGML_TYPE_F32;
case GGML_OP_OUT_PROD: