Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,5 @@ 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
+llama_float16_tp2_rank0.engine filter=lfs diff=lfs merge=lfs -text
+llama_float16_tp2_rank1.engine filter=lfs diff=lfs merge=lfs -text

config.json

@@ -0,0 +1,54 @@
+{
+  "builder_config": {
+    "gather_all_token_logits": false,
+    "hidden_act": "silu",
+    "hidden_size": 7168,
+    "int8": false,
+    "lora_target_modules": [],
+    "max_batch_size": 12,
+    "max_beam_width": 1,
+    "max_input_len": 3500,
+    "max_num_tokens": null,
+    "max_output_len": 1000,
+    "max_position_embeddings": 4096,
+    "max_prompt_embedding_table_size": 0,
+    "name": "llama",
+    "num_heads": 56,
+    "num_kv_heads": 8,
+    "num_layers": 60,
+    "parallel_build": false,
+    "pipeline_parallel": 1,
+    "precision": "float16",
+    "quant_mode": 0,
+    "tensor_parallel": 2,
+    "use_refit": false,
+    "vocab_size": 64000
+  },
+  "plugin_config": {
+    "attention_qk_half_accumulation": false,
+    "bert_attention_plugin": false,
+    "context_fmha_type": 0,
+    "gemm_plugin": "float16",
+    "gpt_attention_plugin": "float16",
+    "identity_plugin": false,
+    "layernorm_plugin": false,
+    "layernorm_quantization_plugin": false,
+    "lookup_plugin": false,
+    "lora_plugin": false,
+    "multi_block_mode": false,
+    "nccl_plugin": "float16",
+    "paged_kv_cache": true,
+    "quantize_per_token_plugin": false,
+    "quantize_tensor_plugin": false,
+    "remove_input_padding": true,
+    "rmsnorm_plugin": false,
+    "rmsnorm_quantization_plugin": false,
+    "smooth_quant_gemm_plugin": false,
+    "tokens_per_block": 128,
+    "use_context_fmha_for_generation": false,
+    "use_custom_all_reduce": false,
+    "use_paged_context_fmha": false,
+    "weight_only_groupwise_quant_matmul_plugin": false,
+    "weight_only_quant_matmul_plugin": false
+  }
+}

llama_float16_tp2_rank0.engine

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee741bf249ef518d3f7e80efa5abc70c60ac050a8e655f4983c1a2851f768b3b
+size 34857021044

llama_float16_tp2_rank1.engine

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54ddf354e1122d12010af4667bf9e124182f09e6cad5c575f90cda0029ef5405
+size 34857021044