addinge engine model

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+*.engine filter=lfs diff=lfs merge=lfs -text

engine/config.json

@@ -0,0 +1,157 @@
+{
+    "version": "0.10.0",
+    "pretrained_config": {
+        "architecture": "Phi3ForCausalLM",
+        "dtype": "float16",
+        "logits_dtype": "float32",
+        "vocab_size": 32064,
+        "max_position_embeddings": 4096,
+        "hidden_size": 3072,
+        "num_hidden_layers": 32,
+        "num_attention_heads": 32,
+        "num_key_value_heads": 32,
+        "head_size": 96,
+        "qk_layernorm": false,
+        "hidden_act": "swiglu",
+        "intermediate_size": 8192,
+        "norm_epsilon": 1e-05,
+        "position_embedding_type": "learned_absolute",
+        "use_parallel_embedding": false,
+        "embedding_sharding_dim": 0,
+        "share_embedding_table": false,
+        "mapping": {
+            "world_size": 1,
+            "tp_size": 1,
+            "pp_size": 1,
+            "gpus_per_node": 8
+        },
+        "quantization": {
+            "quant_algo": null,
+            "kv_cache_quant_algo": null,
+            "group_size": 128,
+            "smoothquant_val": null,
+            "has_zero_point": false,
+            "pre_quant_scale": false,
+            "exclude_modules": null
+        },
+        "kv_dtype": "float16",
+        "rope_theta": 10000.0,
+        "rotary_base": 10000.0
+    },
+    "build_config": {
+        "max_input_len": 1024,
+        "max_output_len": 1024,
+        "opt_batch_size": null,
+        "max_batch_size": 8,
+        "max_beam_width": 1,
+        "max_num_tokens": 8192,
+        "opt_num_tokens": 8,
+        "max_prompt_embedding_table_size": 0,
+        "gather_context_logits": false,
+        "gather_generation_logits": false,
+        "strongly_typed": false,
+        "builder_opt": 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": "NVIDIA-GeForce-RTX-3090",
+            "cluster_info": {
+                "inter_node_bw_per_device": 25,
+                "intra_node_bw_per_device": 300,
+                "inter_node_latency": 10,
+                "intra_node_latency": 10,
+                "intra_node_sharp": false,
+                "inter_node_sharp": true,
+                "memory_bw": 936,
+                "memory_budget_per_device": 24,
+                "math_throughput": {
+                    "int4": 705,
+                    "int8": 352,
+                    "fp8": 0,
+                    "float16": 176,
+                    "bfloat16": 176,
+                    "float32": 88
+                },
+                "memory_efficiency": 1.0,
+                "math_efficiency": 1.0,
+                "communication_efficiency": 1.0
+            },
+            "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*"
+            ],
+            "fast_reduce": true,
+            "fill_weights": false,
+            "parallel_config_cache": null,
+            "profile_cache": null,
+            "dump_path": null,
+            "debug_outputs": []
+        },
+        "weight_sparsity": false,
+        "weight_streaming": false,
+        "use_strip_plan": false,
+        "max_encoder_input_len": 1024,
+        "use_fused_mlp": false,
+        "plugin_config": {
+            "bert_attention_plugin": "float16",
+            "gpt_attention_plugin": "float16",
+            "gemm_plugin": "float16",
+            "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": "float16",
+            "mamba_conv1d_plugin": "float16",
+            "context_fmha": true,
+            "context_fmha_fp32_acc": false,
+            "paged_kv_cache": true,
+            "remove_input_padding": true,
+            "use_custom_all_reduce": true,
+            "multi_block_mode": false,
+            "enable_xqa": true,
+            "attention_qk_half_accumulation": false,
+            "tokens_per_block": 64,
+            "use_paged_context_fmha": false,
+            "use_fp8_context_fmha": false,
+            "use_context_fmha_for_generation": false,
+            "multiple_profiles": false,
+            "paged_state": true,
+            "streamingllm": false
+        }
+    }
+}

engine/rank0.engine

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2af025c8f1fb953cf8b8e2e91b98e3e945e8405a5a97a64849955e4431502d8e
+size 7646867396