microsoft/onnxruntime

Pull Requests Commits

support dll loading in pybind

chentaMS committed 4 years ago

71ff9faf

initial pybind test code

chentaMS committed 4 years ago

34955955

chentaMS committed 4 years ago

1958b2d5

put Tanh on fp32

chentaMS committed 5 years ago

14981fe3

temp fix in layernorm

chentaMS committed 5 years ago

6bac4082

ort training fix

chentaMS committed 5 years ago

6084a987

config to use non std optinal, to avoid confliction with c++ 17

chentaMS committed 5 years ago

559aa993

add bfloat16 to gathergrad type constrains (#6267)

souptc committed 5 years ago

Verified 431604ef

Fix Linux/Mac error message on input type mismatch (#6256)

hariharans29 committed 5 years ago

Verified 2347de4a

Allow querying a GraphProto's doc_string as part of ModelMetadata (#6248)

hariharans29 committed 5 years ago

Verified d42399e1

model parallel refinement (#6244)

pengwa committed 5 years ago

Verified eea3806d

Liqun/speech model loop to scan (#6070)

liqunfu committed 5 years ago

Verified addb4b8c

Add MakeStringLite which uses current locale, update some MakeString call sites to use it instead. (#6252)

edgchen1 committed 5 years ago

Verified ce6161cf

Add the Concat Slice Elimination transform, fix constant_folding transform (#5457)

ashbhandare committed 5 years ago

Verified 493bf931

Remove a debug log in provider_test_utils.cc (#6200)

Changming Sun committed 5 years ago

Verified 6fd9d34b

Documentation for distributed CI tests pipeline (#6140)

baijumeswani committed 5 years ago

Verified 93bf7c4d

Refactor EP Perf Tool (#6202)

oliviajain committed 5 years ago

Verified c8de3f35

Tune BiasGeluGradDx kernel in approximation mode to avoid tanh(...) on Rocm (#6239)

Suffian Khan committed 5 years ago

Verified 46e0e4e6

Fix allocator issue for TensorRT IOBinding (#6240)

HectorSVC committed 5 years ago

Verified ffb4b628

Update manylinux docker image to the latest (#6242)

Changming Sun committed 5 years ago

Verified 1685167e

Update BUILD.md

Changming Sun committed 5 years ago

d5cb17c6

Support double for operator ArgMin (#6222)

xadupre committed 5 years ago

Verified cd14c1af

Support double for operator ReduceMean, ReduceLogSumExp (#6217)

xadupre committed 5 years ago

Verified 84addcd2

Support double for operator Gemm + fix bug in gemm implementation for cuda, rocm when sizeof(type) != sizeof(float) (#6223)

xadupre committed 5 years ago

Verified 5968a91e

Support double for operator TopK + fix one bug in TopK implementation for GPU for double (#6220)

xadupre committed 5 years ago

Verified 70e2f96e

MLAS: handle MlasGemm(M/N/K==0) cases (#6238)

tracysh committed 5 years ago

Verified ecb2e119

Support MLFloat16 type in Pow opset-12 CUDA kernel (#6233)

hariharans29 committed 5 years ago

Verified 4cc2ffef

Upgrade build.py to assert for python 3.6+

WilliamTambellini committed 5 years ago

39a988ce

Update the readme file

Changming Sun committed 5 years ago

c15a8587

Remove python 3.5

Changming Sun committed 5 years ago

3911105f

Older