Skip to content

Zo support#192

Draft
JanCSEM wants to merge 89 commits into
pulp-platform:develfrom
JanCSEM:zo-support
Draft

Zo support#192
JanCSEM wants to merge 89 commits into
pulp-platform:develfrom
JanCSEM:zo-support

Conversation

@JanCSEM
Copy link
Copy Markdown

@JanCSEM JanCSEM commented May 12, 2026

Describe the intent of your PR here.

Added

Changed

Fixed

PR Merge Checklist

  1. The PR is rebased on the latest devel commit and pointing to devel.
  2. Your PR reviewed and approved.
  3. All checks are passing.
  4. The CHANGELOG.md file has been updated.
  5. If the docker was modified, change back its link after review.

runwangdl and others added 30 commits February 12, 2026 15:27
@runwangdl
Deeploy Microbenchmark with GVSoC CSR and Demo on GEMM
49cddd2
@runwangdl
Add float concat and Change padding pattern of ConV
b260e4e
@runwangdl
Merge branch 'devel' into sleepvit
7b55d0a
@runwangdl
Support SleepViT on Gap9
5a79c79
@runwangdl
Add microbenchmark to codepass
609179c
@Xeratec
Add GAP9 Container Support
bedec91 
- Cleanup Docker flow to use a temporary build folder
- Install zsh and oh-my-zsh plugin
- Adapt GAP9 Docker Flow to support ARM64
- Add GAP9 Docker GitHub Build Flow
- Add GAP9 Run script to use real hardware
- Update README
- Fix missing pre-commit dependency

WIP
@Xeratec
Fix spelling mistakes and remove dependencies from fork
97c2d2b
@Xeratec
Fix Missing Version Link
3423c54
@Xeratec
Temporarily disable GAP9 on forks
d6b6ac9
@Xeratec
Add Shell Format pre-commit
daf8cda
@Xeratec
Update to GAP9 SDK v5.21.1-staging-1
f1c7d57
@Xeratec
Print memory usage by default
646563d
@Xeratec
Cleanup Makefile
b2b43a5
@Xeratec
Try to fix private GAP9 SDK access issue
1a075d0
@Xeratec
Use pre-build GAP9 GCC
2bb1bf5
@Xeratec
Fix Typos
af405a2
@Xeratec
Partially revert a16c1c7
c6bc2c6 
We still need x86 compilation for Autotiler
@Xeratec
Build AutoTiler
d325f79
@Xeratec
CodeAIRabbit Feedback
53b4bb9
@Xeratec
Update Changelog
6d1c8c3
@Xeratec
CodeAIRabbit Feedback
6db1c52
@JanCSEM
Add single kernel tests for random perturbations
ba6c1e8
@JanCSEM
Add ZO model tests
90edc44
@JanCSEM
Cherry picked NCHW->NHWC transform issue
4bcefd3
@JanCSEM
FIX: Bug in conv2D parser assigning kernel shape regardless of channe…
44699b2 
…ls_first state
@JanCSEM
Fix compilation bugs caused by ZO nodes
2b5f611
@Victor-Jung
Add option to deploy on the board for the GAP9 platform
846d4dd
@Victor-Jung
WIP: Better error message when attaching usbip and vid + pid of the n…
ae3c4d1 
…ew evk GAP9 board
@JanCSEM
remove prints
02ac6c9
@JanCSEM
Remove debugging test, add Eggroll test+
5911375
JanCSEM and others added 30 commits March 6, 2026 08:53
@JanCSEM
Adding noise kernel microbenchmarks
1f82f07
@JanCSEM
Optimized kernels with function call removals and loop unrolling
a1a5369
@JanCSEM
Fix redundant seed mixing
90d75ad
.gitignore
7a7564e
fix merge conflicts
f45542a
Optimize Ziggurat and Box-muller kernels
43a798b
@JanCSEM
update LiteCNN tests, and added QLiteCNN tests
43902a6
@JanCSEM
add labels to ZO graph inputs
143ad15
@JanCSEM
Fix inputs.npz for ZO graphs
c18af62
@JanCSEM
update inputs.npz
66888da
@JanCSEM
Rename loss to log prob to not upset deeploy
769abe7
ZO softmax cross entropy debug
0f7c1a2
@JanCSEM
Fix issues with shapes being integer
12f311a
@JanCSEM
Fix QLiteCNN, add support for Tiled Quant/Dequant nodes
8483963
@JanCSEM
Noise test updates
701e60c
@JanCSEM
Add integer Random Noise kernels
871d07b
@JanCSEM
Add RQS Kernel tests
1b01b67
@JanCSEM
Bug fixes on quantized noise graphs
b68ad2d
@JanCSEM
Debug RQSPerturb tiling and type checks for quantized nodes
7c50c5c
@JanCSEM
Add Passing QLiteCNN, QSleepViT and ZO versions
c0ab98c
@JanCSEM
update zo_models_benchmarks
61ebc20
@JanCSEM
Optimize QSleepViT memory
849f54a
@JanCSEM
update tests with non-tiled versions matching python model
ebb7228
@JanCSEM
Add exception o convert requant to cmsis if onputs come from rqspertu…
bd4d0e4 
…rbstion
@JanCSEM
Separate quantization kernels
be86c5a
@JanCSEM
update perturbation templates
729454c
@JanCSEM
Workaround o3 optimization issue for randomnoise.c
0cdba94
@JanCSEM
Add cores argument to DeeployRunner instead of using default
239d657
@JanCSEM
Update C perturbation kernels
d588548
@JanCSEM
restore rounding in adddrequantmergepAss
fe366d1
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

@Victor-Jung Victor-Jung Awaiting requested review from Victor-Jung Victor-Jung will be requested when the pull request is marked ready for review Victor-Jung is a code owner

@Xeratec Xeratec Awaiting requested review from Xeratec Xeratec will be requested when the pull request is marked ready for review Xeratec is a code owner

@runwangdl runwangdl Awaiting requested review from runwangdl runwangdl will be requested when the pull request is marked ready for review runwangdl is a code owner

Copilot code review Copilot Awaiting requested review from Copilot Copilot will automatically review once the pull request is marked ready for review

At least 1 approving review is required to merge this pull request.

Assignees

No one assigned

Labels

None yet

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

4 participants

@JanCSEM @runwangdl @Xeratec @Victor-Jung