Skip to content
Closed
Changes from all commits
Commits
Show all changes
18 commits
Select commit Hold shift + click to select a range
b8538f9
deps(zonnx): bump github.com/zerfoo/zmf to v0.2.0; tests passing
dndungu Aug 25, 2025
8a011a5
fix: convert flags
dndungu Aug 25, 2025
32b00c2
feat(zonnx/converter): add TENSOR attrs, UINT8/INT8, Constant, MatMul…
dndungu Mar 2, 2026
2a7bd4f
feat(converter): promote Slice/Pad/TopK input tensors to ZMF attributes
dndungu Mar 2, 2026
04726bb
feat(importer/layers): add Softmax, Sigmoid, Erf, LayerNorm, Slice, P…
dndungu Mar 2, 2026
8c51c89
feat(converter): add Resize special case and skip empty optional inpu…
dndungu Mar 2, 2026
2ea318d
feat(importer/layers): add Conv, GlobalAveragePool, BatchNormalizatio…
dndungu Mar 2, 2026
bb132a2
feat(importer/layers): add MoEGate and MixtureOfExperts stubs (T40.3)
dndungu Mar 2, 2026
8830eb5
fix(importer): load ONNX external data for model initializers
dndungu Mar 4, 2026
2bb6bf3
deps(zonnx): bump zmf to v0.3.0 for Attribute_Tensor support
dndungu Mar 4, 2026
949570c
fix(converter): add BOOL tensor data type support
dndungu Mar 4, 2026
a1dfa04
fix(converter): keep integer initializer inputs as graph references
dndungu Mar 4, 2026
0c8b52a
Merge zerfoo/main into main
dndungu Mar 4, 2026
e9a6fc6
feat(quantize): add Q4_0/Q8_0 weight quantization package
dndungu Mar 5, 2026
391b15c
feat(cli): add --quantize flag to convert command
dndungu Mar 5, 2026
00ba8f2
fix(quantize): skip norm, embedding, bias, and small tensors
dndungu Mar 6, 2026
a5cfb56
fix(quantize): skip 1D tensors from Q4/Q8 quantization
dndungu Mar 9, 2026
9a9a96b
Merge remote-tracking branch 'zerfoo/main'
dndungu Mar 10, 2026
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view

These merge commits were added into this branch cleanly.

There are no new changes to show.