Add TensorRT-LLM engine files for Mistral-7B-instruct-v0.2 compiled on Windows 11 NVIDIA GeForce RTX 3080Ti for single GPU mode.

.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
+llama_float16_tp1_rank0.engine filter=lfs diff=lfs merge=lfs -text

config.json

@@ -0,0 +1,53 @@
+{
+  "builder_config": {
+    "gather_all_token_logits": false,
+    "hidden_act": "silu",
+    "hidden_size": 4096,
+    "int8": true,
+    "max_batch_size": 1,
+    "max_beam_width": 1,
+    "max_input_len": 3000,
+    "max_num_tokens": null,
+    "max_output_len": 1024,
+    "max_position_embeddings": 32768,
+    "max_prompt_embedding_table_size": 0,
+    "name": "llama",
+    "num_heads": 32,
+    "num_kv_heads": 8,
+    "num_layers": 32,
+    "parallel_build": false,
+    "pipeline_parallel": 1,
+    "precision": "float16",
+    "quant_mode": 34,
+    "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,
+    "lora_plugin": false,
+    "multi_block_mode": false,
+    "nccl_plugin": false,
+    "paged_kv_cache": false,
+    "quantize_per_token_plugin": false,
+    "quantize_tensor_plugin": false,
+    "remove_input_padding": false,
+    "rmsnorm_plugin": false,
+    "rmsnorm_quantization_plugin": false,
+    "smooth_quant_gemm_plugin": false,
+    "tokens_per_block": 0,
+    "use_context_fmha_for_generation": false,
+    "use_custom_all_reduce": false,
+    "use_paged_context_fmha": false,
+    "weight_only_groupwise_quant_matmul_plugin": "float16",
+    "weight_only_quant_matmul_plugin": false
+  }
+}

llama_float16_tp1_rank0.engine

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cdffeb5d22b110c81ca75e6e0089d280315e56dac5c99d9dab0dc898cf080899
+size 4196446172