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
+whisper_decoder_float16_tp1_rank0.engine filter=lfs diff=lfs merge=lfs -text
+whisper_encoder_float16_tp1_rank0.engine filter=lfs diff=lfs merge=lfs -text

decoder_config.json

@@ -0,0 +1,57 @@
+{
+  "builder_config": {
+    "apply_query_key_layer_scaling": false,
+    "cross_attention": true,
+    "has_position_embedding": true,
+    "has_token_type_embedding": false,
+    "hidden_act": "gelu",
+    "hidden_size": 1280,
+    "int8": true,
+    "max_batch_size": 8,
+    "max_beam_width": 5,
+    "max_input_len": 224,
+    "max_output_len": 512,
+    "max_position_embeddings": 448,
+    "name": "whisper_decoder",
+    "num_heads": 20,
+    "num_layers": 32,
+    "precision": "float16",
+    "strongly_typed": false,
+    "tensor_parallel": 1,
+    "use_refit": false,
+    "vocab_size": 51865
+  },
+  "plugin_config": {
+    "attention_qk_half_accumulation": false,
+    "bert_attention_plugin": null,
+    "context_fmha": true,
+    "context_fmha_fp32_acc": false,
+    "enable_xqa": false,
+    "gemm_plugin": "float16",
+    "gpt_attention_plugin": "float16",
+    "identity_plugin": null,
+    "layernorm_quantization_plugin": null,
+    "lookup_plugin": null,
+    "lora_plugin": null,
+    "mamba_conv1d_plugin": null,
+    "moe_plugin": null,
+    "multi_block_mode": false,
+    "multiple_profiles": false,
+    "nccl_plugin": null,
+    "paged_kv_cache": false,
+    "paged_state": false,
+    "quantize_per_token_plugin": false,
+    "quantize_tensor_plugin": false,
+    "remove_input_padding": false,
+    "rmsnorm_quantization_plugin": null,
+    "smooth_quant_gemm_plugin": null,
+    "streamingllm": false,
+    "tokens_per_block": 128,
+    "use_context_fmha_for_generation": false,
+    "use_custom_all_reduce": false,
+    "use_fp8_context_fmha": false,
+    "use_paged_context_fmha": false,
+    "weight_only_groupwise_quant_matmul_plugin": null,
+    "weight_only_quant_matmul_plugin": "float16"
+  }
+}

encoder_config.json

@@ -0,0 +1,50 @@
+{
+  "builder_config": {
+    "hidden_size": 1280,
+    "int8": true,
+    "max_batch_size": 8,
+    "max_beam_width": 5,
+    "n_mels": 80,
+    "name": "whisper_encoder",
+    "num_heads": 20,
+    "num_languages": 99,
+    "num_layers": 32,
+    "precision": "float16",
+    "strongly_typed": false,
+    "tensor_parallel": 1,
+    "use_refit": false
+  },
+  "plugin_config": {
+    "attention_qk_half_accumulation": false,
+    "bert_attention_plugin": "float16",
+    "context_fmha": true,
+    "context_fmha_fp32_acc": false,
+    "enable_xqa": false,
+    "gemm_plugin": "float16",
+    "gpt_attention_plugin": null,
+    "identity_plugin": null,
+    "layernorm_quantization_plugin": null,
+    "lookup_plugin": null,
+    "lora_plugin": null,
+    "mamba_conv1d_plugin": null,
+    "moe_plugin": null,
+    "multi_block_mode": false,
+    "multiple_profiles": false,
+    "nccl_plugin": null,
+    "paged_kv_cache": false,
+    "paged_state": false,
+    "quantize_per_token_plugin": false,
+    "quantize_tensor_plugin": false,
+    "remove_input_padding": false,
+    "rmsnorm_quantization_plugin": null,
+    "smooth_quant_gemm_plugin": null,
+    "streamingllm": false,
+    "tokens_per_block": 128,
+    "use_context_fmha_for_generation": false,
+    "use_custom_all_reduce": false,
+    "use_fp8_context_fmha": false,
+    "use_paged_context_fmha": false,
+    "weight_only_groupwise_quant_matmul_plugin": null,
+    "weight_only_quant_matmul_plugin": "float16"
+  }
+}

whisper_decoder_float16_tp1_rank0.engine

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2557df8832f1166b6df390410c7185cc67be0da5f80c35e165b8891b80d62c64
+size 1117801596

whisper_encoder_float16_tp1_rank0.engine

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5eec6f28e51d0ff6acefb5d560234d3227040ae5acf7d993e62869961598ef3d
+size 650081924