onecc-docker

lp:onecc-docker

Created by twoflower and last modified
Get this branch:
bzr branch lp:onecc-docker

Related bugs

Related blueprints

Branch information

Owner:
one-compiler
Project:
onecc-docker
Status:
Merged

Import details

Import Status: Failed

This branch is an import of the HEAD branch of the Git repository at https://github.com/Samsung/ONE.git.

The import has been suspended because it failed 5 or more times in succession.

Last successful import was .

Import started on juju-1e3bde-prod-lp-code-import-14 and finished taking 10 seconds — see the log
Import started on juju-1e3bde-prod-lp-code-import-15 and finished taking 10 seconds — see the log
Import started on juju-1e3bde-prod-lp-code-import-14 and finished taking 10 seconds — see the log
Import started on juju-1e3bde-prod-lp-code-import-13 and finished taking 10 seconds — see the log

Recent revisions

7029. By Jiyoung Giuliana Yun <email address hidden>

[onecc-docker] Change debian file locations (#9806)

This commit changes debian file locations to build in root
directory.

ONE-DCO-1.0-Signed-off-by: Jiyoung Yun <email address hidden>

7028. By Hyukjin Jeong <email address hidden>

[luci] Skip checks for S32/S64 Add (#9805)

This skips type/granularity checks for index-typed Add.

ONE-DCO-1.0-Signed-off-by: Hyukjin Jeong <email address hidden>

7027. By Hyeongseok Oh <email address hidden>

[onert/test] Remove boost dependency on NNAPI gtest (#9804)

This commit removes depdency with boost on NNAPI gtest. To remove depdency, NNAPI gtest build uses c++17.

ONE-DCO-1.0-Signed-off-by: Hyeongseok Oh <email address hidden>

7026. By Hyeongseok Oh <email address hidden>

[infra/runtime] Revisit TFLite 2.8 build (#9792)

This commit revisits TFLite 2.8 build CMake to udate based on updated cmake in official tensorflow's cmake.

ONE-DCO-1.0-Signed-off-by: Hyeongseok Oh <email address hidden>

7025. By Hyukjin Jeong <email address hidden>

[luci] Quantize fp32 nodes only (#9803)

This quantizes fp32 nodes only.

ONE-DCO-1.0-Signed-off-by: Hyukjin Jeong <email address hidden>

7024. By Sanggyu Lee <email address hidden>

[nnpkg_tools/qnf] Introduce qnf (#9637)

It introduces a tool named qnf, which is used for quantize and
dequantize using given circle model's input/output qparams.

ONE-DCO-1.0-Signed-off-by: Sanggyu Lee <email address hidden>

7023. By Hyeongseok Oh <email address hidden>

[onert] Change Bulk shape inference batch check (#9797)

This commit changes valid batch size check for bulk operation on static shape inference.

ONE-DCO-1.0-Signed-off-by: Hyeongseok Oh <email address hidden>

7022. By Hyukjin Jeong <email address hidden>

[luci] Use different name for FQ node (#9796)

This uses different names for fake-quantized nodes.

ONE-DCO-1.0-Signed-off-by: Hyukjin Jeong <email address hidden>

7021. By Hyeongseok Oh <email address hidden>

[onert] Support multiple model on builtin backend (#9795)

This commit updates builtin backend to support multiple model on controlflow.

ONE-DCO-1.0-Signed-off-by: Hyeongseok Oh <email address hidden>

7020. By Jang Jiseob <email address hidden>

[onert] Support batch-parallel execution of trix models (#9747)

This commit suppors batch-parallel execution of trix models.
  - Introduce BatchThreadPool
  - Gather things related to device handle in DevContext
  - Change ir::Shape::MAX_RANK to ir::Shape::ONERT_MAX_RANK

ONE-DCO-1.0-Signed-off-by: ragmani <email address hidden>

Branch metadata

Branch format:
Branch format 7
Repository format:
Bazaar repository format 2a (needs bzr 1.16 or later)
This branch contains Public information 
Everyone can see this information.

Subscribers