onnxruntime/onnxruntime/core
Hector Li b5d1a49b30
Share allocator between CUDA EP & TRT EP. (#6332)
* Share allocator between CUDA EP & TRT EP.
limitation:
1. Does not cover the per-thread allocator created by CUDA EP, still need to figure out the way to remove it
2. Need to have more identifiers to make it able to share CPU allocator across all EPs
2021-01-27 00:14:43 -08:00
..
codegen Add ability to filter GraphViewer using IndexedSubGraph. (#5614) 2020-11-04 07:08:18 +10:00
common Remove false positive prefast warning from threadpool (#6324) 2021-01-12 14:47:52 -08:00
dll
flatbuffers Allow querying a GraphProto's doc_string as part of ModelMetadata (#6248) 2021-01-05 22:18:03 -08:00
framework Share allocator between CUDA EP & TRT EP. (#6332) 2021-01-27 00:14:43 -08:00
graph Add support for custom ops to minimal build. (#6228) 2021-01-25 10:41:00 +10:00
language_interop_ops Change the OrtCustomOp invocation as a constant. (#5506) 2020-11-02 10:38:07 -08:00
mlas MLAS: add fallback implementation for quantized GEMM (#6335) 2021-01-13 10:53:47 -08:00
optimizer Fix some compile warnings (#6316) 2021-01-21 16:40:42 -08:00
platform Rename MakeString and ParseString functions. (#6272) 2021-01-07 15:43:42 -08:00
profile Pipeline Parallel Experimental Python API (#5815) 2021-01-15 12:07:28 +08:00
protobuf
providers Share allocator between CUDA EP & TRT EP. (#6332) 2021-01-27 00:14:43 -08:00
session Share allocator between CUDA EP & TRT EP. (#6332) 2021-01-27 00:14:43 -08:00
util Fix some compile warnings (#6316) 2021-01-21 16:40:42 -08:00