maga_transformer/config/gpt_init_model_parameters.py [106:234]: - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - activation_type: str add_bias_linear: bool block_nums: int cache_store_connect_port: int cache_store_listen_port: int cache_store_rdma_connect_port: int cache_store_rdma_listen_port: int cache_store_rdma_mode: bool ckpt_path: str cross_attn_input_len: int data_type: str decode_polling_kv_cache_step_ms: int decode_retry_timeout_ms: int decode_retry_times: int decode_use_async_load_cache: bool deepseek_mscale_all_dim: float deepseek_rope_mscale: float dp_rank: int dp_size: int dp_tp_nccl_port: int embedding_size: int enable_eplb: bool enable_fast_gen: bool enable_partial_fallback: bool enable_sp: bool enable_speculative_decoding: bool ep_rank: int ep_size: int eplb_mode: EplbMode eplb_update_time: int expert_num: int fast_gen_max_context_len: int ffn_tp_nccl_port: int ffn_tp_rank: int ffn_tp_size: int gen_num_per_circle: int has_lm_head: bool has_moe_norm: bool has_positional_encoding: bool has_post_decoder_layernorm: bool has_pre_decoder_layernorm: bool head_num: int head_num_kv: int hidden_size: int http_port: int include_sep_tokens: bool input_embedding_scalar: float input_vocab_size: int inter_padding_size: int inter_size: int is_causal: bool is_multimodal: bool is_sparse_head: bool kv_cache_data_type: str kv_cache_mem_mb: int kv_lora_rank: int layer_head_num: list[int] layer_head_num_kv: list[int] layer_inter_padding_size: list[int] layer_inter_size: list[int] layer_num: int layernorm_eps: float layernorm_type: str load_balance_policy_name: str load_cache_timeout_ms: int local_rank: int logit_scale: float max_context_batch_size: int max_generate_batch_size: int max_rpc_timeout_ms: int max_seq_len: int mla_ops_type: MlaOpsType mm_position_ids_style: int mm_sep_tokens: list[list[int]] model_name: str model_rpc_port: int moe_inter_padding_size: int moe_k: int moe_layer_index: list[int] moe_n_group: int moe_normalize_expert_scale: bool moe_style: int moe_topk_group: int mrope_section: list[int] nccl_ip: str nope_head_dim: int norm_type: str num_layers: int num_valid_layer: int org_embedding_max_pos: int pd_sep_enable_fallback: bool pd_separation: bool phy_exp_num: int position_id_len_factor: int position_ids_style: int pre_allocate_op_mem: bool pre_seq_len: int prefill_max_wait_timeout_ms: int prefill_retry_timeout_ms: int prefill_retry_times: int prefix_projection: bool py_eplb: typing.Any q_lora_rank: int q_scaling: float qk_norm: bool quant_algo: QuantAlgo rdma_connect_retry_times: int remote_rpc_server_port: int reserve_runtime_mem_mb: int residual_scalar: float reuse_cache: bool reverse_e_h_norm: bool rope_head_dim: int rotary_embedding_base: float rotary_embedding_dim: int rotary_embedding_mscale: float rotary_embedding_offset: int rotary_embedding_scale: float rotary_embedding_style: int rotary_factor1: float rotary_factor2: float scheduler_reserve_resource_ratio: int scoring_func: int seq_size_per_block: int size_per_head: int softmax_extra_scale: float special_tokens: SpecialTokens tokenizer_path: str tp_nccl_port: int - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - maga_transformer/ops/libth_transformer.pyi [132:260]: - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - activation_type: str add_bias_linear: bool block_nums: int cache_store_connect_port: int cache_store_listen_port: int cache_store_rdma_connect_port: int cache_store_rdma_listen_port: int cache_store_rdma_mode: bool ckpt_path: str cross_attn_input_len: int data_type: str decode_polling_kv_cache_step_ms: int decode_retry_timeout_ms: int decode_retry_times: int decode_use_async_load_cache: bool deepseek_mscale_all_dim: float deepseek_rope_mscale: float dp_rank: int dp_size: int dp_tp_nccl_port: int embedding_size: int enable_eplb: bool enable_fast_gen: bool enable_partial_fallback: bool enable_sp: bool enable_speculative_decoding: bool ep_rank: int ep_size: int eplb_mode: EplbMode eplb_update_time: int expert_num: int fast_gen_max_context_len: int ffn_tp_nccl_port: int ffn_tp_rank: int ffn_tp_size: int gen_num_per_circle: int has_lm_head: bool has_moe_norm: bool has_positional_encoding: bool has_post_decoder_layernorm: bool has_pre_decoder_layernorm: bool head_num: int head_num_kv: int hidden_size: int http_port: int include_sep_tokens: bool input_embedding_scalar: float input_vocab_size: int inter_padding_size: int inter_size: int is_causal: bool is_multimodal: bool is_sparse_head: bool kv_cache_data_type: str kv_cache_mem_mb: int kv_lora_rank: int layer_head_num: list[int] layer_head_num_kv: list[int] layer_inter_padding_size: list[int] layer_inter_size: list[int] layer_num: int layernorm_eps: float layernorm_type: str load_balance_policy_name: str load_cache_timeout_ms: int local_rank: int logit_scale: float max_context_batch_size: int max_generate_batch_size: int max_rpc_timeout_ms: int max_seq_len: int mla_ops_type: MlaOpsType mm_position_ids_style: int mm_sep_tokens: list[list[int]] model_name: str model_rpc_port: int moe_inter_padding_size: int moe_k: int moe_layer_index: list[int] moe_n_group: int moe_normalize_expert_scale: bool moe_style: int moe_topk_group: int mrope_section: list[int] nccl_ip: str nope_head_dim: int norm_type: str num_layers: int num_valid_layer: int org_embedding_max_pos: int pd_sep_enable_fallback: bool pd_separation: bool phy_exp_num: int position_id_len_factor: int position_ids_style: int pre_allocate_op_mem: bool pre_seq_len: int prefill_max_wait_timeout_ms: int prefill_retry_timeout_ms: int prefill_retry_times: int prefix_projection: bool py_eplb: typing.Any q_lora_rank: int q_scaling: float qk_norm: bool quant_algo: QuantAlgo rdma_connect_retry_times: int remote_rpc_server_port: int reserve_runtime_mem_mb: int residual_scalar: float reuse_cache: bool reverse_e_h_norm: bool rope_head_dim: int rotary_embedding_base: float rotary_embedding_dim: int rotary_embedding_mscale: float rotary_embedding_offset: int rotary_embedding_scale: float rotary_embedding_style: int rotary_factor1: float rotary_factor2: float scheduler_reserve_resource_ratio: int scoring_func: int seq_size_per_block: int size_per_head: int softmax_extra_scale: float special_tokens: SpecialTokens tokenizer_path: str tp_nccl_port: int - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -