forked from jiuyuan/InfiniTensor
feccd4f318
* fix Slice * change default rounds of timeit to 10 to reduce time * fix slice with large ends * Reshape support Int64 * support position_ids as input * skip last MatMul in Llama * skip infer_shapes to parse large model * update launch.py * fix split_concat_kernel * print more message in launch.py * Reshape supports both Int32 and Int64 * try infer_shapes and warn about failure * fix format --------- Co-authored-by: whjthu <haojie0429@gmail.com> |
||
|---|---|---|
| .. | ||
| blob.h | ||
| common.h | ||
| communicator.h | ||
| constants.h | ||
| data_type.h | ||
| dummy_mutator.h | ||
| graph.h | ||
| graph_handler.h | ||
| graph_match.h | ||
| hash.h | ||
| kernel.h | ||
| lazy_allocator.h | ||
| mutator.h | ||
| object.h | ||
| op_type.h | ||
| operator.h | ||
| perf_engine.h | ||
| ref.h | ||
| runtime.h | ||
| search_engine.h | ||
| tensor.h | ||
| tensor_base.h | ||
| tensor_type.h | ||