Commits: backends/vulkan/_passes/__init__.py - dhruvhead/executorch - Morph

SIGN IN SIGN UP

dhruvhead / executorch UNCLAIMED

0 0 1 Python

COMMITS

/ backends/vulkan/_passes/__init__.py

test

May 8, 2025

P

[ET-VK] Introduce generic export pass for fusing Q/DQ nodes (#10771)

pytorchbot committed 1y ago

February 20, 2025

N

update SqueezeInt4LinearInputs to process relu/gelu inputs too

Nathanael See committed 1y ago

February 6, 2025

P

[ET-VK][int4] Wrap int4 linear calls with view_copy nodes to squeeze/unsqueeze inputs

pytorchbot committed 1y ago

January 31, 2025

S

Split SDPA + KV cache operator into SDPA operator and KV cache update operator + Add `RemoveAsserts` pass and apply it during LlaMa export

Sicheng Stephen Jia committed 1y ago

December 16, 2024

P

[ET-VK] Add pass to remove copy ops (#7326)

pytorchbot committed 1y ago

November 5, 2024

P

[ET-VK] Introduce memory metadata tagging pass (#6669)

pytorchbot committed 1y ago

October 18, 2024

S

Implement prepack nodes (#6352)

Stephen Jia committed 1y ago

October 16, 2024

S

Add custom `VkInt4WeightOnlyQuantizer` for vulkan (#6234)

Stephen Jia committed 1y ago

October 10, 2024

S

Update `RemoveLocalScalarDenseOpsTransform` to tag scalar tensors as well (#6069)

Stephen Jia committed 1y ago