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
QMatmulGPURepackGPTQ_b4_g128_desc_act
struct QMatmulGPURepackGPTQ_b4_g128_desc_act
Implemented traitsβ
AnyType,
ImplicitlyDestructible
Methodsβ
executeβ
static def execute[target: StringSlice[StaticConstantOrigin], _trace_name: StringSlice[StaticConstantOrigin]](b_packed: ManagedTensorSlice[Output, static_spec=b_packed.static_spec], b: ManagedTensorSlice[Input, static_spec=b.static_spec], perm_idx: ManagedTensorSlice[Input, static_spec=perm_idx.static_spec], ctx: DeviceContext)
shapeβ
static def shape(b: ManagedTensorSlice[Input, static_spec=b.static_spec], perm_idx: ManagedTensorSlice[Input, static_spec=perm_idx.static_spec]) -> IndexList[2]
Returns:
Was this page helpful?
Thank you! We'll create more content like this.
Thank you for helping us improve!