nm-testing/kv_cache_fp8-e2e

1{2  "architectures": [3    "LlamaForCausalLM"4  ],5  "attention_bias": false,6  "bos_token_id": 1,7  "eos_token_id": 2,8  "hidden_act": "silu",9  "hidden_size": 2048,10  "initializer_range": 0.02,11  "intermediate_size": 5632,12  "max_position_embeddings": 2048,13  "model_type": "llama",14  "num_attention_heads": 32,15  "num_hidden_layers": 22,16  "num_key_value_heads": 4,17  "pretraining_tp": 1,18  "quantization_config": {19    "config_groups": {},20    "format": "dense",21    "global_compression_ratio": null,22    "ignore": [],23    "kv_cache_scheme": {24      "actorder": null,25      "block_structure": null,26      "dynamic": false,27      "group_size": null,28      "num_bits": 8,29      "observer": null,30      "observer_kwargs": {},31      "scale_dtype": null,32      "strategy": "tensor",33      "symmetric": true,34      "type": "float",35      "zp_dtype": null36    },37    "quant_method": "compressed-tensors",38    "quantization_status": "compressed",39    "sparsity_config": {},40    "transform_config": {},41    "version": "0.19.1a20260919"42  },43  "rms_norm_eps": 1e-05,44  "rope_scaling": null,45  "rope_theta": 10000.0,46  "tie_word_embeddings": false,47  "torch_dtype": "bfloat16",48  "transformers_version": "4.35.0",49  "use_cache": true,50  "vocab_size": 3200051}