Collection on FP8 Quantization of Weights, Activations and KV Cache
NM Testing
company
AI & ML interests
None defined yet.
Recent Activity
View all activity
-
nm-testing/Meta-Llama-3-8B-Instruct-W8A8-FP8-Channelwise-compressed-tensors
Text Generation • 8B • Updated • 13 • 2 -
nm-testing/Meta-Llama-3-8B-Instruct-FBGEMM-nonuniform
Text Generation • 8B • Updated • 4 -
nm-testing/Meta-Llama-3-8B-FP8-compressed-tensors-test
Text Generation • 8B • Updated • 18.4k -
nm-testing/Meta-Llama-3-8B-Instruct-W8-Channel-A8-Dynamic-Asym-Per-Token-Test
8B • Updated • 4.92k • 1
Collection on FP8 Quantization of Weights, Activations and KV Cache
-
nm-testing/Meta-Llama-3-8B-Instruct-W8A8-FP8-Channelwise-compressed-tensors
Text Generation • 8B • Updated • 13 • 2 -
nm-testing/Meta-Llama-3-8B-Instruct-FBGEMM-nonuniform
Text Generation • 8B • Updated • 4 -
nm-testing/Meta-Llama-3-8B-FP8-compressed-tensors-test
Text Generation • 8B • Updated • 18.4k -
nm-testing/Meta-Llama-3-8B-Instruct-W8-Channel-A8-Dynamic-Asym-Per-Token-Test
8B • Updated • 4.92k • 1
models 523
nm-testing/w4a16_moe-e2e
31B • Updated • 74
nm-testing/w8a8_static_asym-e2e
1B • Updated • 670
nm-testing/Qwen3-30B-A3B-NVFP4-AWQ-e2e
17B • Updated • 450
nm-testing/w8a8_dynamic_asym-e2e
1B • Updated • 677
nm-testing/w8a16_grouped_quant-e2e
1B • Updated • 702
nm-testing/w4a16_sym_awq-e2e
1B • Updated • 651
nm-testing/w4a16_grouped_quant-e2e
1B • Updated • 667
nm-testing/w4a16_asym_awq-e2e
1B • Updated • 708
nm-testing/w4a16_actorder_weight-e2e
1B • Updated • 652
nm-testing/w4a16_actorder_group-e2e
1B • Updated • 706
datasets 6
nm-testing/ultrachat_gpt_oss_20b_hidden_states
Updated • 96 • 1
nm-testing/sharegpt_qwen3_8b_hidden_states
Updated • 148
nm-testing/ultrachat_qwen3_8b_hidden_states
Updated • 81
nm-testing/sharegpt_llama3_8b_token_freq
Updated • 21
nm-testing/sharegpt_llama3_8b_hidden_states
Viewer • Updated • 1 • 183
nm-testing/qa-chat-prompts
Viewer • Updated • 200 • 36 • 2
