checkpoint

.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

.gitignore

@@ -0,0 +1 @@
+.env

1-gpu/config.json

@@ -0,0 +1,47 @@
+{
+  "builder_config": {
+    "fp8": false,
+    "hidden_act": "silu",
+    "hidden_size": 4096,
+    "int8": false,
+    "max_batch_size": 8,
+    "max_input_len": 2048,
+    "max_num_tokens": null,
+    "max_output_len": 512,
+    "max_position_embeddings": 4096,
+    "name": "llama",
+    "num_heads": 32,
+    "num_kv_heads": 32,
+    "num_layers": 32,
+    "parallel_build": false,
+    "pipeline_parallel": 1,
+    "precision": "float16",
+    "quant_mode": 0,
+    "tensor_parallel": 1,
+    "use_refit": false,
+    "vocab_size": 32000
+  },
+  "plugin_config": {
+    "attention_qk_half_accumulation": false,
+    "bert_attention_plugin": false,
+    "context_fmha_type": 1,
+    "gemm_plugin": "float16",
+    "gpt_attention_plugin": "float16",
+    "identity_plugin": false,
+    "layernorm_plugin": false,
+    "layernorm_quantization_plugin": false,
+    "lookup_plugin": false,
+    "nccl_plugin": false,
+    "paged_kv_cache": false,
+    "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": 0,
+    "use_custom_all_reduce": false,
+    "weight_only_groupwise_quant_matmul_plugin": false,
+    "weight_only_quant_matmul_plugin": false
+  }
+}

1-gpu/llama_float16_tp1_rank0.engine

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a7558d8628cbe8ce2e09377743fe47d33235d33b201fb23ebffd1b6d6ca1905
+size 13480868308