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 • 24 • 2 -
nm-testing/Meta-Llama-3-8B-Instruct-FBGEMM-nonuniform
Text Generation • 8B • Updated -
nm-testing/Meta-Llama-3-8B-FP8-compressed-tensors-test
Text Generation • 8B • Updated • 7.9k -
nm-testing/Meta-Llama-3-8B-Instruct-W8-Channel-A8-Dynamic-Asym-Per-Token-Test
8B • Updated • 4 • 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 • 24 • 2 -
nm-testing/Meta-Llama-3-8B-Instruct-FBGEMM-nonuniform
Text Generation • 8B • Updated -
nm-testing/Meta-Llama-3-8B-FP8-compressed-tensors-test
Text Generation • 8B • Updated • 7.9k -
nm-testing/Meta-Llama-3-8B-Instruct-W8-Channel-A8-Dynamic-Asym-Per-Token-Test
8B • Updated • 4 • 1
models 510
nm-testing/TinyLlama-1.1B-Chat-v1.0-W8A8-Static-Asym-e2e
1B • Updated • 715
nm-testing/TinyLlama-1.1B-Chat-v1.0-W8A8-Dynamic-Asym-e2e
1B • Updated • 385
nm-testing/TinyLlama-1.1B-Chat-v1.0-W8A16-e2e
1B • Updated • 533
nm-testing/TinyLlama-1.1B-Chat-v1.0-W8A16_channel-e2e
1B • Updated • 427
nm-testing/TinyLlama-1.1B-Chat-v1.0-w4a16-sym-awq-e2e
1B • Updated • 332
nm-testing/TinyLlama-1.1B-Chat-v1.0-w4a16-asym-awq-e2e
1B • Updated • 381
nm-testing/TinyLlama-1.1B-Chat-v1.0-W4A16-e2e
1B • Updated • 16.9k
nm-testing/TinyLlama-1.1B-Chat-v1.0-W4A16_channel-e2e
1B • Updated • 405
nm-testing/TinyLlama-1.1B-Chat-v1.0-actorder-weight-e2e
1B • Updated • 400
nm-testing/TinyLlama-1.1B-Chat-v1.0-actorder-none-e2e
1B • Updated • 380
datasets 6
nm-testing/ultrachat_gpt_oss_20b_hidden_states
Updated • 68
nm-testing/sharegpt_qwen3_8b_hidden_states
Updated • 62
nm-testing/ultrachat_qwen3_8b_hidden_states
Updated • 68
nm-testing/sharegpt_llama3_8b_token_freq
Updated • 7
nm-testing/sharegpt_llama3_8b_hidden_states
Viewer • Updated • 1 • 248
nm-testing/qa-chat-prompts
Viewer • Updated • 200 • 15 • 2