| { | |
| "_serialized_key": "NxDNeuronConfig", | |
| "batch_size": 1, | |
| "capacity_factor": null, | |
| "checkpoint_id": "meta-llama/Llama-3.2-1B", | |
| "checkpoint_revision": "4e20de362430cd3b72f300e6b0f18e50e7166e08", | |
| "continuous_batching": false, | |
| "ep_degree": 1, | |
| "fused_qkv": true, | |
| "glu_mlp": true, | |
| "local_ranks_size": 4, | |
| "max_batch_size": 1, | |
| "max_context_length": 128, | |
| "max_topk": 256, | |
| "n_active_tokens": 128, | |
| "neuronxcc_version": "2.21.18209.0+043b1bf7", | |
| "on_device_sampling": true, | |
| "optimum_neuron_version": "0.4.1", | |
| "output_logits": false, | |
| "pp_degree": 1, | |
| "sequence_length": 128, | |
| "speculation_length": 0, | |
| "start_rank_id": 0, | |
| "target": "inf2", | |
| "torch_dtype": "bfloat16", | |
| "tp_degree": 4 | |
| } | |