( self, input_size: int, output_size: int, bias: bool = False, tp_dim:

( self, hidden_size: int, intermediate_size: int, hidden_act: str, )

(numerator, denominator)

(self, hash: int, token_ids: list[int])

(self, seq: Sequence)

(self, i)

(self, method_name, *args)

(cls, token_ids: list[int], prefix: int = -1)

( self, prompts: list[str] | list[list[int]], sampling_params: SamplingParams | list[S

()

(is_prefill, cu_seqlens_q=None, cu_seqlens_k=None, max_seqlen_q=0, max_seqlen_k=0, slot_mapping=None, context_

(self)

( x: torch.Tensor, cos: torch.Tensor, sin: torch.Tensor, )

( self, hidden_states: torch.Tensor, )

(self, seq: Sequence)

(self, seq: Sequence)

(self, seqs: list[Sequence])

()

( self, num_embeddings: int, embedding_dim: int, bias: bool = False, )

(self, block_id: int)

(self, prompt: str | list[int], sampling_params: SamplingParams)

( self, x: torch.Tensor, residual: torch.Tensor, )

(self, seq: Sequence, num_cached_blocks: int)

(self)

(self, token_id: int)

(self, seq: Sequence)

(self, seq: Sequence)

(self)

( head_size: int, rotary_dim: int, max_position: int, base: float, )

(self, seq: Sequence)

(self)

(model: nn.Module, path: str)

(self)

()

()

(self, seq: Sequence)

(self, seqs: list[Sequence], token_ids: list[int], is_prefill: bool)

(self, seqs: list[Sequence])

(self, seqs: list[Sequence])

(self, seqs: list[Sequence])

(self)

(self)

( self, x: torch.Tensor, )

(self, seqs: list[Sequence], is_prefill: bool)

(self, input_ids: torch.Tensor, positions: torch.Tensor, is_prefill: bool)

(self)

(self)

(key: torch.Tensor, value: torch.Tensor, k_cache: torch.Tensor, v_cache: torch.Tensor, slot_mapping: torch.Ten

(self)

(self, method_name, *args)

(self, key)

(self)

(self, config: Config)

(self, block_id)

(self, num_blocks: int, block_size: int)

(self, config: Config, rank: int, event: Event | list[Event])

(self, token_ids: list[int], sampling_params = SamplingParams())

(self, model, **kwargs)

( self, hidden_size: int, eps: float = 1e-6, )

( self, num_embeddings: int, embedding_dim: int, )

( self, input_size: int, output_size: int, bias: bool = False, )

( self, input_size: int, output_size: int, bias: bool = False, )

( self, input_size: int, output_sizes: list[int], bias: bool = False, )

( self, hidden_size: int, head_size: int, total_num_heads: int, total_

( self, input_size: int, output_size: int, bias: bool = False, )

( self, head_size: int, rotary_dim: int, max_position_embeddings: int,

( self, num_heads, head_dim, scale, num_kv_heads, )

( self, hidden_size: int, num_heads: int, num_kv_heads: int, max_posit

( self, config: Qwen3Config, )

( self, config: Qwen3Config, )

( self, config: Qwen3Config )

(self)

(self)

(self)

(self, state)

(self)

(param: nn.Parameter, loaded_weight: torch.Tensor)

(self)

(self)

( self, x: torch.Tensor, residual: torch.Tensor | None = None, )

(self, x: torch.Tensor)

(self, x: torch.Tensor)

(self, x: torch.Tensor)

(self, x: torch.Tensor)

(self, x: torch.Tensor)

(self, x: torch.Tensor)

( self, positions: torch.Tensor, query: torch.Tensor, key: torch.Tensor, )

(self, q: torch.Tensor, k: torch.Tensor, v: torch.Tensor)

(self, logits: torch.Tensor, temperatures: torch.Tensor)

(self, x: torch.Tensor)

( self, positions: torch.Tensor, hidden_states: torch.Tensor, )

(self, x)

( self, positions: torch.Tensor, hidden_states: torch.Tensor, residual: torch.

( self, input_ids: torch.Tensor, positions: torch.Tensor, )

( self, input_ids: torch.Tensor, positions: torch.Tensor, )

(self)

(self)

(self)

(self)

(self)