microsoft/onnxruntime

Pull Requests Commits

fs-eire committed 1 year ago

e2aeb21d

Add attrProto.release_s interface (#22977)

danyue333 committed 1 year ago

Verified 62e7e24f

Fix the ctx_gen tool to make sure all generated ctx.onnx have max_size (#23097)

HectorSVC committed 1 year ago

Verified 2a36fd4f

Backward compatible with old QNN version (#23095)

HectorSVC committed 1 year ago

Verified f43f40fa

[js/webgpu] fix Conv2DMatMul shader's out-of-bound read (#23085)

fs-eire committed 1 year ago

Verified 01539ee7

Remove deprecated static from Eigen that contributes to size increase (#23084)

yuslepukhin committed 1 year ago

Verified 890a719c

OVEP 1.21.0 Development Updates (#23080)

ankitm3k committed 1 year ago

Verified 1f88284f

disable the EP context embed model by default in session option (#23070)

HectorSVC committed 1 year ago

Verified ebb968d3

[js/web] Update API for `ort.env.webgpu` (#23026)

fs-eire committed 1 year ago

Verified e6058707

Implement 2d tiled matmulnbits specialized for prefill (#23058)

sushraja-msft committed 1 year ago

Verified 8800830a

[CUDA EP] Fix BeamSearch on T5 with sequence_as_input_ids (#20667) (#20668)

amancini-N committed 1 year ago

Verified d8de3c40

[WebNN] Improve data type check of slice op (#22988)

shiyi9801 committed 1 year ago

Verified 02f0af0d

Minor updates to onnxruntime_java.cmake (#23068)

edgchen1 committed 1 year ago

Verified fa6ad202

[webgpu] Optimize Expand (#23052)

qjia7 committed 1 year ago

Verified defcc4f8

Update vcpkg.json - lock flatbuffer version (#23046)

mc-nv committed 1 year ago

Verified bf4d3e1a

Upgrade gradle to 8.7 (#23016)

jchen351 committed 1 year ago

Verified 5f7b9d02

Restore Qspectre flag (#23060)

A-Satti committed 1 year ago

Verified b14b4ec7

Reduce default logger usage (#23030)

skottmckay committed 1 year ago

Verified 708ee855

[CoreML] more performace flag (#22975)

wejoncy committed 1 year ago

Verified e12421be

Fix BeamSearch T5 if initializers are on outer scope (#23044)

amancini-N committed 1 year ago

Verified 8f3384b4

Miscellaneous cleanups (#23048)

skottmckay committed 1 year ago

Verified 2f2c73bd

[webgpu] Add Alias def for Flatten (#23038)

fs-eire committed 1 year ago

Verified 22ae97c7

[WebNN] Allow ops to handle ignoring an empty tensor as input (#22972)

Honry committed 1 year ago

Verified 6d9636f0

Update Intel Thread Counts (#22894)

A-Satti committed 1 year ago

Verified f5293d25

[ARM CPU] Add rotary embedding fp16 kernel (#23013)

fajin-corp committed 1 year ago

Verified bd5a759d

Enable QNN HTP spill fill buffer setting to save RAM usage. (#22853)

HectorSVC committed 1 year ago

Verified 401d16c6

Bump cross-spawn from 6.0.5 to 6.0.6 in /js/web (#23019)

dependabot[bot] committed 1 year ago

Verified d27fecd3

Deprecate macos-12 (#23017)

mszhanyi committed 1 year ago

Verified 6ed77cc3

[js/common] use TS type inference to eliminate `unknown` (#23012)

fs-eire committed 1 year ago

Verified 1c79a4c9

Adding DML to python cuda package (#22606)

jchen351 committed 1 year ago

Verified f340b3ca

Older