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

change.txt

@@ -0,0 +1,4 @@
+nvlink change only works on nvlink stuff change the id in the build.py file
+and you  might get an error for the custom_id still(works 50/50)you will 
+need to debug the cuda assigning then
+when running make sure its on an sxm Nvidia gpu which has Nvlink

config.json

@@ -0,0 +1,54 @@
+{
+  "builder_config": {
+    "gather_all_token_logits": false,
+    "hidden_act": "swiglu",
+    "hidden_size": 4096,
+    "int8": false,
+    "lora_target_modules": [],
+    "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,
+    "name": "llama",
+    "num_heads": 32,
+    "num_kv_heads": 8,
+    "num_layers": 32,
+    "parallel_build": true,
+    "pipeline_parallel": 1,
+    "precision": "float16",
+    "quant_mode": 0,
+    "tensor_parallel": 2,
+    "use_refit": false,
+    "vocab_size": 32002
+  },
+  "plugin_config": {
+    "attention_qk_half_accumulation": false,
+    "bert_attention_plugin": false,
+    "context_fmha_type": 1,
+    "gemm_plugin": false,
+    "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 sha256:49400a103297acb964b1c65aca18ef879425326fc117abfe81cd145ea09c10ea
+size 46842531828

llama_float16_tp2_rank1.engine

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92d559fcade958c0ef66bf98a480c054fae0cc6969cc09aac6d20b5dcfa9c6c5
+size 46842531828