add quantized fast_hadamard_transform_28N#5184

Closed

swolchok wants to merge 67 commits intogh/swolchok/37/headfrom

gh/swolchok/38/head

Commits on Sep 9, 2024

Commits on Sep 10, 2024

Commits on Sep 11, 2024

fbshipit-source-id: f63634ba171da01328849d84552b125b829403e8
facebook-github-bot
committed
Minibench use model_dir instead (#5250)

kirklandsign
authored and
facebook-github-bot
committed
Update setup.sh for LlamaDemo (#5235)

kirklandsign
authored and
facebook-github-bot
committed
Android app UI/flow improvements (#5241)

Riandy
authored and
facebook-github-bot
committed
Allow core aten op exception list (#5237)

larryliu0820
authored and
facebook-github-bot
committed
link whole quantized_ops_lib (#5253)

kirklandsign
authored and
facebook-github-bot
committed
spinquant in eager mode (#5125)

Lunwen He
authored and
facebook-github-bot
committed
Updated the workflow to upload models to S3 (#5232)

Guang Yang
authored and
facebook-github-bot
committed
Add model execution scripts and runner (#5217)

neuropilot-captain
authored and
facebook-github-bot
committed
Debug event populates event name (#5142)

Olivia-liu
authored and
facebook-github-bot
committed
Optimized op_mm using CPUBlas gemm (#5242)

swolchok
authored and
facebook-github-bot
committed
Add optimized op_linear (#5243)

swolchok
authored and
facebook-github-bot
committed
Add scalar tensor tests. (#5260)

shoumikhin
authored and
facebook-github-bot
committed
Add CoreML Quantize (#5228)

yifan_shen3
authored and
facebook-github-bot
committed
Add helper function to create empty, full, ones and zeros tensors. (#5261)

shoumikhin
authored and
facebook-github-bot
committed
Add helper function to create random tensors. (#5266)

shoumikhin
authored and
facebook-github-bot
committed
Update base for Update on "add quantized fast_hadamard_transform_28N"
swolchok
committed
Update on "add quantized fast_hadamard_transform_28N"
swolchok
committed