kylesayrs/Meta-Llama-3-8B-Instruct-FP8-yes_quant-layer-sequential-noprop
Updated
•
10
Kyle Sayers
kylesayrs
AI & ML interests
Accelerating ML inference @ Red Hat
Recent Activity
updated
a model
11 days ago
nm-testing/Llama-2-7b-hf-weight-input-quant-compressed
published
a model
11 days ago
nm-testing/Llama-2-7b-hf-weight-input-quant-compressed
updated
a model
11 days ago
nm-testing/Llama-2-7b-hf-weight-input-quant-uncompressed
Organizations
models
6
kylesayrs/Meta-Llama-3-8B-Instruct-FP8-no_quant-layer-sequential-noprop
Updated
•
10
kylesayrs/Meta-Llama-3-8B-Instruct-FP8-no_quant-linear
Updated
•
26
kylesayrs/Meta-Llama-3-8B-Instruct-FP8-yes_quant-linear
Updated
•
8
kylesayrs/Meta-Llama-3-8B-Instruct-FP8-yes_quant-layer
Updated
•
58
kylesayrs/Meta-Llama-3-8B-Instruct-FP8-no_quant-layer
Updated
•
9
datasets
0
None public yet