Delete trt_engines.b256/unimernet/1-gpu/bfloat16/decoder/config.json

trt_engines.b256/unimernet/1-gpu/bfloat16/decoder/config.json

@@ -1,168 +0,0 @@
-{
-    "version": "0.12.0",
-    "pretrained_config": {
-        "architecture": "DecoderModel",
-        "dtype": "bfloat16",
-        "vocab_size": 50000,
-        "hidden_size": 1024,
-        "num_hidden_layers": 8,
-        "num_attention_heads": 16,
-        "hidden_act": "gelu",
-        "logits_dtype": "float32",
-        "norm_epsilon": false,
-        "position_embedding_type": "learned_absolute",
-        "max_position_embeddings": 1536,
-        "num_key_value_heads": 16,
-        "intermediate_size": 4096,
-        "mapping": {
-            "world_size": 1,
-            "gpus_per_node": 8,
-            "cp_size": 1,
-            "tp_size": 1,
-            "pp_size": 1,
-            "moe_tp_size": 1,
-            "moe_ep_size": 1
-        },
-        "quantization": {
-            "quant_algo": null,
-            "kv_cache_quant_algo": null,
-            "group_size": 128,
-            "smoothquant_val": 0.5,
-            "clamp_val": null,
-            "has_zero_point": false,
-            "pre_quant_scale": false,
-            "exclude_modules": null
-        },
-        "use_parallel_embedding": false,
-        "embedding_sharding_dim": 0,
-        "share_embedding_table": false,
-        "head_size": 64,
-        "qk_layernorm": false,
-        "has_position_embedding": true,
-        "layernorm_type": 0,
-        "has_attention_qkvo_bias": true,
-        "has_mlp_bias": true,
-        "has_model_final_layernorm": true,
-        "has_embedding_layernorm": true,
-        "has_embedding_scale": true,
-        "q_scaling": 1.0,
-        "layernorm_position": 0,
-        "mlp_type": 0,
-        "relative_attention": false,
-        "max_distance": 0,
-        "num_buckets": 0,
-        "model_type": "bart",
-        "rescale_before_lm_head": false,
-        "encoder_hidden_size": 1024,
-        "encoder_num_heads": 16,
-        "encoder_head_size": 64,
-        "skip_cross_qkv": false,
-        "use_implicit_relative_attention": false,
-        "decoder_start_token_id": null,
-        "eos_token_id": 2,
-        "bos_token_id": 0,
-        "pad_token_id": 1,
-        "gated_act": false,
-        "type_vocab_size": null,
-        "encoder_num_kv_heads": null,
-        "residual_scaling": 1.0,
-        "has_lm_head_bias": false
-    },
-    "build_config": {
-        "max_input_len": 1,
-        "max_seq_len": 101,
-        "opt_batch_size": null,
-        "max_batch_size": 256,
-        "max_beam_width": 1,
-        "max_num_tokens": 8192,
-        "opt_num_tokens": 256,
-        "max_prompt_embedding_table_size": 0,
-        "gather_context_logits": false,
-        "gather_generation_logits": false,
-        "strongly_typed": true,
-        "builder_opt": null,
-        "force_num_profiles": null,
-        "profiling_verbosity": "layer_names_only",
-        "enable_debug_output": false,
-        "max_draft_len": 0,
-        "speculative_decoding_mode": 1,
-        "use_refit": false,
-        "input_timing_cache": null,
-        "output_timing_cache": "model.cache",
-        "lora_config": {
-            "lora_dir": [],
-            "lora_ckpt_source": "hf",
-            "max_lora_rank": 64,
-            "lora_target_modules": [],
-            "trtllm_modules_to_hf_modules": {}
-        },
-        "auto_parallel_config": {
-            "world_size": 1,
-            "gpus_per_node": 8,
-            "cluster_key": "A100-SXM-80GB",
-            "cluster_info": null,
-            "sharding_cost_model": "alpha_beta",
-            "comm_cost_model": "alpha_beta",
-            "enable_pipeline_parallelism": false,
-            "enable_shard_unbalanced_shape": false,
-            "enable_shard_dynamic_shape": false,
-            "enable_reduce_scatter": true,
-            "builder_flags": null,
-            "debug_mode": false,
-            "infer_shape": true,
-            "validation_mode": false,
-            "same_buffer_io": {
-                "past_key_value_(\\d+)": "present_key_value_\\1"
-            },
-            "same_spec_io": {},
-            "sharded_io_allowlist": [
-                "past_key_value_\\d+",
-                "present_key_value_\\d*"
-            ],
-            "fill_weights": false,
-            "parallel_config_cache": null,
-            "profile_cache": null,
-            "dump_path": null,
-            "debug_outputs": []
-        },
-        "weight_sparsity": false,
-        "weight_streaming": false,
-        "plugin_config": {
-            "dtype": "bfloat16",
-            "bert_attention_plugin": "bfloat16",
-            "gpt_attention_plugin": "bfloat16",
-            "gemm_plugin": "bfloat16",
-            "gemm_swiglu_plugin": null,
-            "fp8_rowwise_gemm_plugin": null,
-            "smooth_quant_gemm_plugin": null,
-            "identity_plugin": null,
-            "layernorm_quantization_plugin": null,
-            "rmsnorm_quantization_plugin": null,
-            "nccl_plugin": null,
-            "lookup_plugin": null,
-            "lora_plugin": null,
-            "weight_only_groupwise_quant_matmul_plugin": null,
-            "weight_only_quant_matmul_plugin": null,
-            "quantize_per_token_plugin": false,
-            "quantize_tensor_plugin": false,
-            "moe_plugin": null,
-            "mamba_conv1d_plugin": "auto",
-            "context_fmha": true,
-            "bert_context_fmha_fp32_acc": false,
-            "paged_kv_cache": false,
-            "remove_input_padding": true,
-            "reduce_fusion": false,
-            "enable_xqa": false,
-            "tokens_per_block": 64,
-            "use_paged_context_fmha": false,
-            "use_fp8_context_fmha": false,
-            "multiple_profiles": false,
-            "paged_state": true,
-            "streamingllm": false,
-            "manage_weights": false
-        },
-        "use_strip_plan": false,
-        "max_encoder_input_len": 588,
-        "use_fused_mlp": false
-    }
-}