File size: 1,679 Bytes
6b2fe2d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
{
  "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": 512,
    "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": 8,
    "num_layers": 6,
    "precision": "float16",
    "strongly_typed": false,
    "tensor_parallel": 1,
    "use_refit": false,
    "vocab_size": 51864
  },
  "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"
  }
}