A | B | C | E | F | I | L | M | O | P | Q | R | S | T | W

F: fp32_thread_args; Fp32CLIPAttention; Fp32CLIPAttention_input; Fp32CLIPAttention_output; Fp32CLIPEncoder; Fp32CLIPEncoder_input; Fp32CLIPEncoder_output; Fp32CLIPEncoderLayer; Fp32CLIPEncoderLayer_input; Fp32CLIPEncoderLayer_output; Fp32CLIPVisionTransformer; Fp32CLIPVisionTransformer_input; Fp32CLIPVisionTransformer_output; Fp32GPTBigCodeAttention; Fp32GPTBigCodeAttention_input; Fp32GPTBigCodeAttention_output; Fp32GPTBigCodeDecoder; Fp32GPTBigCodeDecoder_input; Fp32GPTBigCodeDecoder_output; Fp32GPTBigCodeDecoderLayer; Fp32GPTBigCodeDecoderLayer_input; Fp32GPTBigCodeDecoderLayer_output; Fp32GPTBigCodeForCausalLM; Fp32GPTBigCodeForCausalLM_input; Fp32GPTBigCodeForCausalLM_output; Fp32llamaAttention; Fp32llamaAttention_input; Fp32llamaAttention_output; Fp32llamaDecoder; Fp32llamaDecoder_input; Fp32llamaDecoder_output; Fp32llamaDecoderLayer; Fp32llamaDecoderLayer_input; Fp32llamaDecoderLayer_output; Fp32LlamaForCausalLM; Fp32LlamaForCausalLM_input; Fp32LlamaForCausalLM_output; Fp32OPTAttention; Fp32OPTAttention_input; Fp32OPTAttention_output; Fp32OPTDecoder; Fp32OPTDecoder_input; Fp32OPTDecoder_output; Fp32OPTDecoderLayer; Fp32OPTDecoderLayer_input; Fp32OPTDecoderLayer_output; Fp32OPTForCausalLM; Fp32OPTForCausalLM_input; Fp32OPTForCausalLM_output

I: int4_thread_args; Int4GPTBigCodeAttention; Int4GPTBigCodeAttention_input; Int4GPTBigCodeAttention_output; Int4GPTBigCodeDecoder; Int4GPTBigCodeDecoder_input; Int4GPTBigCodeDecoder_output; Int4GPTBigCodeDecoderLayer; Int4GPTBigCodeDecoderLayer_input; Int4GPTBigCodeDecoderLayer_output; Int4GPTBigCodeForCausalLM; Int4GPTBigCodeForCausalLM_input; Int4GPTBigCodeForCausalLM_output; Int4llamaAttention; Int4llamaAttention_input; Int4llamaAttention_output; Int4llamaDecoder; Int4llamaDecoder_input; Int4llamaDecoder_output; Int4llamaDecoderLayer; Int4llamaDecoderLayer_input; Int4llamaDecoderLayer_output; Int4LlamaForCausalLM; Int4LlamaForCausalLM_input; Int4LlamaForCausalLM_output; Int4OPTAttention; Int4OPTAttention_input; Int4OPTAttention_output; Int4OPTDecoder; Int4OPTDecoder_input; Int4OPTDecoder_output; Int4OPTDecoderLayer; Int4OPTDecoderLayer_input; Int4OPTDecoderLayer_output; Int4OPTForCausalLM; Int4OPTForCausalLM_input; Int4OPTForCausalLM_output; Int8OPTAttention; Int8OPTAttention_input; Int8OPTAttention_output; Int8OPTDecoder; Int8OPTDecoder_input; Int8OPTDecoder_output; Int8OPTDecoderLayer; Int8OPTDecoderLayer_input; Int8OPTDecoderLayer_output

L: LayerNorm; LayerNorm_params; LayerNormQ; LayerNormQ_params; Linear_FP; Linear_FP_int4; llama_file; llama_sp_bigram; llama_sp_symbol; llama_tokenizer; llama_vocab; LlamaRMSNorm; llava_image_embed

M: matmul_params; MatmulOperator (matmul); matrix; Matrix3D; Matrix4D; max_error_info; MetalMatmulBuffers; MetalMatmulInt4; MetalMatmulInt4IMP; MetalMatMulParams; model_config

O: opt_params; OPT_token_data; OPT_token_data_array; OPTForCausalLM; OPTForCausalLM_input; OPTForCausalLM_output; optimization_params

T: thread_args; llama_vocab::token_score; TokenIndex; Tokenizer; transpose_1_2idx_arg; transpose_1_2idx_float_arg

W: W8A8B8O8Linear; W8A8B8O8Linear_params; W8A8B8O8LinearReLU; W8A8B8O8LinearReLU_params; W8A8BFP32OFP32Linear; W8A8BFP32OFP32Linear_params