Upload folder using huggingface_hub

.gitattributes

@@ -6,3 +6,11 @@ llama_float16_tp8_rank6.engine filter=lfs diff=lfs merge=lfs -text
 llama_float16_tp8_rank7.engine filter=lfs diff=lfs merge=lfs -text
 llama_float16_tp8_rank0.engine filter=lfs diff=lfs merge=lfs -text
 llama_float16_tp8_rank1.engine filter=lfs diff=lfs merge=lfs -text
+TP_bf16/llama_bfloat16_tp8_rank0.engine filter=lfs diff=lfs merge=lfs -text
+TP_bf16/llama_bfloat16_tp8_rank1.engine filter=lfs diff=lfs merge=lfs -text
+TP_bf16/llama_bfloat16_tp8_rank2.engine filter=lfs diff=lfs merge=lfs -text
+TP_bf16/llama_bfloat16_tp8_rank3.engine filter=lfs diff=lfs merge=lfs -text
+TP_bf16/llama_bfloat16_tp8_rank4.engine filter=lfs diff=lfs merge=lfs -text
+TP_bf16/llama_bfloat16_tp8_rank5.engine filter=lfs diff=lfs merge=lfs -text
+TP_bf16/llama_bfloat16_tp8_rank6.engine filter=lfs diff=lfs merge=lfs -text
+TP_bf16/llama_bfloat16_tp8_rank7.engine filter=lfs diff=lfs merge=lfs -text

TP_bf16/config.json

@@ -0,0 +1,57 @@
+{
+  "builder_config": {
+    "autopp_config": null,
+    "gather_context_logits": false,
+    "gather_generation_logits": false,
+    "hidden_act": "swiglu",
+    "hidden_size": 4096,
+    "int8": false,
+    "lora_target_modules": null,
+    "max_batch_size": 8,
+    "max_beam_width": 1,
+    "max_input_len": 2048,
+    "max_num_tokens": null,
+    "max_output_len": 512,
+    "max_position_embeddings": 32768,
+    "max_prompt_embedding_table_size": 0,
+    "mlp_hidden_size": 14336,
+    "name": "llama",
+    "num_heads": 32,
+    "num_kv_heads": 8,
+    "num_layers": 32,
+    "parallel_build": true,
+    "pipeline_parallel": 1,
+    "precision": "bfloat16",
+    "quant_mode": 0,
+    "tensor_parallel": 8,
+    "use_refit": false,
+    "vocab_size": 32000
+  },
+  "plugin_config": {
+    "attention_qk_half_accumulation": false,
+    "bert_attention_plugin": false,
+    "context_fmha_type": 1,
+    "gemm_plugin": "bfloat16",
+    "gpt_attention_plugin": "bfloat16",
+    "identity_plugin": false,
+    "layernorm_plugin": false,
+    "layernorm_quantization_plugin": false,
+    "lookup_plugin": false,
+    "lora_plugin": false,
+    "multi_block_mode": false,
+    "nccl_plugin": "bfloat16",
+    "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
+  }
+}

TP_bf16/llama_bfloat16_tp8_rank0.engine

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b521593c3353683bcc8023ffdd265e3e344bd3643bd27d017d1d707f404f6b7
+size 11911318636

TP_bf16/llama_bfloat16_tp8_rank1.engine

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d45abe370095a528e79be0b43d788ade6003d15c1255af390622b49dfecaf30
+size 11911318636

TP_bf16/llama_bfloat16_tp8_rank2.engine

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7619ed044a18a06ae8ee72654658011227f35bcd93d4c5befe8f4c824e43792c
+size 11911319404

TP_bf16/llama_bfloat16_tp8_rank3.engine

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cadc39d624ef7695c52fb2f362ab0e1153ca62984615007aaea89e6b1dd10992
+size 11911298788

TP_bf16/llama_bfloat16_tp8_rank4.engine

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:447dde6221db7c280802d32f2917f5f9f3c8890df795a2c3d1c42691e894c064
+size 11911318828

TP_bf16/llama_bfloat16_tp8_rank5.engine

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c9a9e96c6b6ae98a58fe4d9c0782324ed1d99947fbe6f08f2146811845e9934
+size 11911318636

TP_bf16/llama_bfloat16_tp8_rank6.engine

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b364c50e4add7de2cb51d83b4d62ba6f7699e6db9b5347bccb4ea613ea01daed
+size 11911319596

TP_bf16/llama_bfloat16_tp8_rank7.engine

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86e55287abb22cf33594511102989c02405ff5fbcd72b5855d570c352f9fa3aa
+size 11911298788