Kyle Sayers's picture

15 3 2

Kyle Sayers

kylesayrs

·

https://github.com/kylesayrs

AI & ML interests

Accelerating ML inference @ Red Hat

Recent Activity

updated a model about 1 month ago

nm-testing/Llama-3.1-8B-Instruct-KV-FP8-tensor-static_minmax

updated a model about 1 month ago

nm-testing/Llama-3.1-8B-Instruct-QKV-FP8-attn_head-static_minmax

published a model about 1 month ago

nm-testing/Llama-3.1-8B-Instruct-QKV-FP8-attn_head-static_minmax

View all activity

Organizations

kylesayrs 's models 8

kylesayrs/Llama-3.2-1B-Instruct-attention-nvfp4-head

1B • Updated Oct 14 • 2

kylesayrs/Llama-3.2-1B-Instruct-attention-fp8-head

1B • Updated Oct 13 • 5

kylesayrs/Meta-Llama-3-8B-Instruct-FP8-yes_quant-layer-sequential-noprop

8B • Updated Apr 1 • 1

kylesayrs/Meta-Llama-3-8B-Instruct-FP8-no_quant-layer-sequential-noprop

8B • Updated Apr 1 • 1

kylesayrs/Meta-Llama-3-8B-Instruct-FP8-no_quant-linear

8B • Updated Apr 1

kylesayrs/Meta-Llama-3-8B-Instruct-FP8-yes_quant-linear

8B • Updated Apr 1 • 1

kylesayrs/Meta-Llama-3-8B-Instruct-FP8-yes_quant-layer

8B • Updated Apr 1 • 1

kylesayrs/Meta-Llama-3-8B-Instruct-FP8-no_quant-layer

8B • Updated Apr 1