For the complete documentation index, see llms.txt. Markdown versions of all pages are available by appending .md to any URL (e.g. /max/get-started.md).
Mojo struct
Struct_fused_qkv_matmul_padded_ragged_bias_quantized
struct Struct_fused_qkv_matmul_padded_ragged_bias_quantized
Implemented traits
AnyType,
ImplicitlyDestructible
Methods
execute
static def execute[dtype: DType, weight_type: DType, group_size: Int, has_zp_int: Int, //, target: StringSlice[StaticConstantOrigin]](output: ManagedTensorSlice[Output, static_spec=output.static_spec], hidden_state: ManagedTensorSlice[Input, static_spec=hidden_state.static_spec], input_row_offsets: ManagedTensorSlice[Input, static_spec=input_row_offsets.static_spec], weight: ManagedTensorSlice[Input, static_spec=weight.static_spec], kv_blocks: ManagedTensorSlice[MutableInput, static_spec=kv_blocks.static_spec], cache_lengths: ManagedTensorSlice[Input, static_spec=cache_lengths.static_spec], kv_lookup_table: ManagedTensorSlice[Input, static_spec=kv_lookup_table.static_spec], max_lengths: ManagedTensorSlice[Input, static_spec=max_lengths.static_spec], layer_idx: UInt32, bias: ManagedTensorSlice[Input, static_spec=bias.static_spec], ctx: DeviceContext)
Was this page helpful?
Thank you! We'll create more content like this.
Thank you for helping us improve!