nm-testing/fp8_dynamic_moe-e2e
31B • Updated • 368
NM Testing
company
AI & ML interests
None defined yet.
Recent Activity
View all activity
nm-testing/w4a16_gptq_smoke-e2e
1B • Updated • 391
nm-testing/llama2.c-stories15M-ultrachat-mixed-uncompressed
24.4M • Updated • 2.72k
nm-testing/Llama-2-7b-hf-gsm8k-quant_w4a16_sym-uncompressed
7B • Updated • 23
nm-testing/Llama-2-7b-hf-gsm8k-gptq_w4a16_sym-uncompressed
7B • Updated • 25
nm-testing/Llama-2-7b-hf-gsm8k-awq_w4a16_sym-uncompressed
7B • Updated • 24
nm-testing/Llama-2-7b-hf-gsm8k-awq_gptq_sym-uncompressed
7B • Updated • 27
nm-testing/Llama-3.2-1B-Instruct-W4A16-uncompressed-mse-hadamard
5B • Updated • 25
nm-testing/llama2.c-stories42M-gsm8k-stacked-uncompressed
58.1M • Updated • 897
nm-testing/llama2.c-stories42M-gsm8k-quantized-only-uncompressed
58.1M • Updated • 3.06k
nm-testing/TinyLlama-1.1B-Chat-v1.0-W8A8-Dynamic-Per-Token-uncompressed
1B • Updated • 277
nm-testing/TinyLlama-1.1B-Chat-v1.0-W8A16-G128-uncompressed
1B • Updated • 326
nm-testing/TinyLlama-1.1B-Chat-v1.0-W4A16-G128-uncompressed
1B • Updated • 267
nm-testing/TinyLlama-1.1B-Chat-v1.0-FP8-Dynamic-uncompressed
1B • Updated • 330
nm-testing/llama2.c-stories15M-pruned_50.2of4-uncompressed-tensor_weights_tensor_act_fp8-BitMaskCompressed
22.2M • Updated • 10
nm-testing/llama-3-fp8-2of4-dynamic-uncompressed
8B • Updated • 13
nm-testing/SparseLlama-3.1-8B-gsm8k-pruned.2of4-FP8-uncompressed
8B • Updated • 21
nm-testing/SparseLlama-3.1-8B-gsm8k-pruned.2of4-quantized.w4a16-uncompressed
2B • Updated • 24
nm-testing/TinyLlama-1.1B-Chat-v1.0-pruned_50.2of4-FP8-uncompressed
1B • Updated • 22
nm-testing/tinyllama-w8a16-dense
1B • Updated • 770
nm-testing/tinyllama-oneshot-w8w8-test-static-shape-change
Text Generation • 1B • Updated • 40k
nm-testing/tinyllama-oneshot-w8a8-static-v2
Text Generation • 1B • Updated • 251
nm-testing/tinyllama-oneshot-w8a8-dynamic-token-v2-asym
Text Generation • 1B • Updated • 225
nm-testing/tinyllama-oneshot-w8a8-dynamic-token-v2
Text Generation • 1B • Updated • 10.5k
nm-testing/tinyllama-oneshot-w8a8-channel-dynamic-token-v2-asym
1B • Updated • 80
nm-testing/tinyllama-oneshot-w8a8-channel-dynamic-token-v2
Text Generation • 1B • Updated • 13k
nm-testing/tinyllama-oneshot-w8a16-per-channel
Text Generation • 1B • Updated • 902
nm-testing/tinyllama-oneshot-w8-channel-a8-tensor
Text Generation • 1B • Updated • 942
nm-testing/tinyllama-oneshot-w4a16-group128-v2
Text Generation • 1B • Updated • 15.2k
nm-testing/tinyllama-oneshot-w4a16-channel-v2
Text Generation • 1B • Updated • 20.1k • 1