52f1096f21
* Thread safety per request only * Fix ROPE yarn case * Fix sticky stateful config * Use i4/i8 directly for symmetric quant * Use weightless caching * Add WeightlessCacheAttribute to reduce NPU memory usage * Gelu tanh support (#125) * Imrope support (#126) * fix(openvino): explicit ov::Tensor frees in ggml_backend_openvino_free * add GPU,NPU support in OV Dockerfile * add build-openvino.yml ci * Fix sticky stateful config * add concurrency to ov-gpu ci runs. Move OV CI to build-openvino.yml * fix thread-safety of shared runtime context * rope type abstraction for frontend translations * fix editorconfig --------- Co-authored-by: Mustafa Cavus <mustafa.cavus@intel.com> Co-authored-by: Dan Hoffman <dhoff749@gmail.com> Co-authored-by: Ravi Panchumarthy <ravi.panchumarthy@intel.com>
41 lines
1.1 KiB
C++
41 lines
1.1 KiB
C++
#pragma once
|
|
|
|
#include "node_context.h"
|
|
|
|
namespace ov {
|
|
namespace frontend {
|
|
namespace ggml {
|
|
|
|
namespace op {
|
|
|
|
#define GGML_OP_CONVERTER(op) OutputVector op(const NodeContext& context)
|
|
|
|
GGML_OP_CONVERTER(translate_add);
|
|
GGML_OP_CONVERTER(translate_cont);
|
|
GGML_OP_CONVERTER(translate_get_rows);
|
|
GGML_OP_CONVERTER(translate_mul);
|
|
GGML_OP_CONVERTER(translate_mulmat);
|
|
GGML_OP_CONVERTER(translate_permute);
|
|
GGML_OP_CONVERTER(translate_reshape);
|
|
GGML_OP_CONVERTER(translate_rms_norm);
|
|
GGML_OP_CONVERTER(translate_rope);
|
|
GGML_OP_CONVERTER(translate_scale);
|
|
GGML_OP_CONVERTER(translate_unary_silu);
|
|
GGML_OP_CONVERTER(translate_unary_gelu);
|
|
GGML_OP_CONVERTER(translate_soft_max);
|
|
GGML_OP_CONVERTER(translate_transpose);
|
|
GGML_OP_CONVERTER(translate_view);
|
|
GGML_OP_CONVERTER(translate_glu_swiglu);
|
|
GGML_OP_CONVERTER(translate_glu_geglu);
|
|
GGML_OP_CONVERTER(translate_set_rows);
|
|
GGML_OP_CONVERTER(translate_cpy);
|
|
GGML_OP_CONVERTER(translate_flash_attn_ext);
|
|
|
|
} // namespace op
|
|
|
|
std::unordered_map<std::string, CreatorFunction> get_supported_ops();
|
|
|
|
} // namespace ggml
|
|
} // namespace frontend
|
|
} // namespace ov
|