happyz
/
llama.cpp
mirror of https://github.com/ggerganov/llama.cpp.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity
llama.cpp/ggml/src/ggml-qnn
History
nullname e36ad89528
bugfix: error pre-allocated tensor (k_cache_view-0) (#12) 
* fix device binding at ggml_backend_qnn_buffer_type

* merge ggml_backend_qnn_buffer_context and qnn_mem_buffer

* wip

* add log

* wip

* add qnn_buffer_ptr

* remove tailing `\n` at log

* add log

* enable GGML_OP_NONE

* wip

* wip

* disable tensor with view

* wip

* wip

* more log for view tensor

* re-enable view

* wip

* remove link android lib

* set dimension at bind function

* move graph traversal to backend-ops

* wip

* add get_view_internal_dimension to obtain the tensor view source dimension

* use _view_source_dimensions to allocate qnn tensor

* add place holder function ggml_backend_qnn_cpy_tensor_async

* add ggml_qnn_aggregate_op_config

* make matmul based on ggml_qnn_aggregate_op_config

* wip

* manually specify the order of op destruct

* skip register qnn-cpu backend

* disable view op again

* remove _view_source_dimensions

* add nop for reshape and view ops

* add log

* add comment
 		2024-12-11 10:42:00 +08:00
..
.clang-format feat: add QNN_OP_TRANSPOSE (#6) 2024-11-04 23:12:03 +08:00
CMakeLists.txt bugfix: error pre-allocated tensor (k_cache_view-0) (#12) 2024-12-11 10:42:00 +08:00
backend-ops.cpp bugfix: error pre-allocated tensor (k_cache_view-0) (#12) 2024-12-11 10:42:00 +08:00
backend-ops.hpp bugfix: error pre-allocated tensor (k_cache_view-0) (#12) 2024-12-11 10:42:00 +08:00
backend.hpp [WIP] feat: perf opt (#10) 2024-11-29 00:03:23 +08:00
buffer.hpp bugfix: error pre-allocated tensor (k_cache_view-0) (#12) 2024-12-11 10:42:00 +08:00
ggml-qnn.cpp bugfix: error pre-allocated tensor (k_cache_view-0) (#12) 2024-12-11 10:42:00 +08:00
graph.hpp bugfix: error pre-allocated tensor (k_cache_view-0) (#12) 2024-12-11 10:42:00 +08:00
logger.cpp [WIP] feat: perf opt (#10) 2024-11-29 00:03:23 +08:00
logger.hpp remove multiply declearation of log in unit test 2024-07-15 12:06:12 +08:00
op-config-base.hpp [WIP] feat: perf opt (#10) 2024-11-29 00:03:23 +08:00
op-config.cpp bugfix: error pre-allocated tensor (k_cache_view-0) (#12) 2024-12-11 10:42:00 +08:00
op-config.hpp bugfix: error pre-allocated tensor (k_cache_view-0) (#12) 2024-12-11 10:42:00 +08:00
qnn-lib.cpp refactoring: prevent leak the QNN_INTERFACE_VER_TYPE and QNN_SYSTEM_INTERFACE_VER_TYPE outside of qnn.hpp 2024-07-17 00:18:38 +08:00
qnn-lib.hpp bugfix: error pre-allocated tensor (k_cache_view-0) (#12) 2024-12-11 10:42:00 +08:00
qnn-types.hpp [WIP] feat: perf opt (#10) 2024-11-29 00:03:23 +08:00
tensor.hpp bugfix: error pre-allocated tensor (k_cache_view-0) (#12) 2024-12-11 10:42:00 +08:00
utils.cpp bugfix: error pre-allocated tensor (k_cache_view-0) (#12) 2024-12-11 10:42:00 +08:00
utils.hpp bugfix: error pre-allocated tensor (k_cache_view-0) (#12) 2024-12-11 10:42:00 +08:00