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 • 5 • 2 -
nm-testing/Meta-Llama-3-8B-Instruct-FBGEMM-nonuniform
Text Generation • 8B • Updated • 5 -
nm-testing/Meta-Llama-3-8B-FP8-compressed-tensors-test
Text Generation • 8B • Updated • 16.6k -
nm-testing/Meta-Llama-3-8B-Instruct-W8-Channel-A8-Dynamic-Asym-Per-Token-Test
8B • Updated • 6.63k • 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 • 5 • 2 -
nm-testing/Meta-Llama-3-8B-Instruct-FBGEMM-nonuniform
Text Generation • 8B • Updated • 5 -
nm-testing/Meta-Llama-3-8B-FP8-compressed-tensors-test
Text Generation • 8B • Updated • 16.6k -
nm-testing/Meta-Llama-3-8B-Instruct-W8-Channel-A8-Dynamic-Asym-Per-Token-Test
8B • Updated • 6.63k • 1
models 510
nm-testing/kv_cache_fp8-e2e
1B • Updated • 75
nm-testing/int8_channel_weight_static_per_tensor_act-e2e
1B • Updated • 73
nm-testing/fp8_static_per_tensor-e2e
1B • Updated • 61 • 1
nm-testing/fp4_nvfp4-e2e
0.7B • Updated • 68
nm-testing/w8a8_static_asym-e2e
1B • Updated • 83
nm-testing/w8a8_dynamic_asym-e2e
1B • Updated • 79
nm-testing/w8a16_grouped_quant-e2e
1B • Updated • 71
nm-testing/w4a16_sym_awq-e2e
1B • Updated • 70
nm-testing/w4a16_grouped_quant-e2e
1B • Updated • 72
nm-testing/w4a16_asym_awq-e2e
1B • Updated • 74
datasets 6
nm-testing/ultrachat_gpt_oss_20b_hidden_states
Updated • 231 • 1
nm-testing/sharegpt_qwen3_8b_hidden_states
Updated • 171
nm-testing/ultrachat_qwen3_8b_hidden_states
Updated • 215
nm-testing/sharegpt_llama3_8b_token_freq
Updated • 17
nm-testing/sharegpt_llama3_8b_hidden_states
Viewer • Updated • 1 • 122
nm-testing/qa-chat-prompts
Viewer • Updated • 200 • 24 • 2