Upload folder using huggingface_hub

.gitattributes

@@ -20,3 +20,5 @@ TP_w2/llama_float16_tp2_rank0.engine filter=lfs diff=lfs merge=lfs -text
 TP_w2/llama_float16_tp2_rank1.engine filter=lfs diff=lfs merge=lfs -text
 PP_w2/llama_float16_tp1_pp2_rank0.engine filter=lfs diff=lfs merge=lfs -text
 PP_w2/llama_float16_tp1_pp2_rank1.engine filter=lfs diff=lfs merge=lfs -text
+PP_bf16_w2/llama_bfloat16_tp2_rank0.engine filter=lfs diff=lfs merge=lfs -text
+PP_bf16_w2/llama_bfloat16_tp2_rank1.engine filter=lfs diff=lfs merge=lfs -text

PP_bf16_w2/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": 2,
+    "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
+  }
+}

PP_bf16_w2/llama_bfloat16_tp2_rank0.engine

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6dde3d1fffd5cfba0025ff2a577f3e80bf89c9ac2561ca24a519fae22854d3b7
+size 46840558068

PP_bf16_w2/llama_bfloat16_tp2_rank1.engine

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac580b33de02b9d2d0696972e4121cd1649c2fd2438cd9af51bd1df82c0b758f
+size 46840557492