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
PreShuffledBGroupedGEMM
struct PreShuffledBGroupedGEMM[cu_count: Int, wg_per_cu: Int = Int(2)]
Implemented traits
comptime members
num_xcd
comptime num_xcd = 8
total_wg
comptime total_wg = (cu_count * wg_per_cu)
wg_per_xcd
comptime wg_per_xcd = (PreShuffledBGroupedGEMM[cu_count, wg_per_cu].total_wg // Int(8))
Methods
to_swizzled_idx
persistent_kernel
static def persistent_kernel[BM: Int, BN: Int, BK_ELEMS: Int, WN: Int, out_dtype: DType, LayoutC: TensorLayout, LayoutA: TensorLayout, LayoutBPre: TensorLayout, LayoutSFA: TensorLayout, LayoutSFB: TensorLayout, AOffsetsLayout: TensorLayout, ExpertIdsLayout: TensorLayout, N: Int, K_BYTES: Int, b_cache_policy: CacheOperation = CacheOperation.ALWAYS, dram_to_lds: Bool = False, cluster_drain_sched: Bool = False, mfma_cluster: Int = Int(4), deep_prime: Bool = False, waves_per_eu: Int = Int(0)](c_tensor: TileTensor[out_dtype, LayoutC, MutAnyOrigin], a_tensor: TileTensor[DType.uint8, LayoutA, ImmutAnyOrigin], b_pre_tensor: TileTensor[DType.uint8, LayoutBPre, ImmutAnyOrigin], sfa_tensor: TileTensor[DType.float8_e8m0fnu, LayoutSFA, ImmutAnyOrigin], sfb_tensor: TileTensor[DType.float8_e8m0fnu, LayoutSFB, ImmutAnyOrigin], a_offsets: TileTensor[DType.uint32, AOffsetsLayout, ImmutAnyOrigin], expert_ids: TileTensor[DType.int32, ExpertIdsLayout, ImmutAnyOrigin], num_active_experts: Int, max_padded_M: Int)
kernel
static def kernel[BM: Int, BN: Int, BK_ELEMS: Int, WN: Int, out_dtype: DType, LayoutC: TensorLayout, LayoutA: TensorLayout, LayoutBPre: TensorLayout, LayoutSFA: TensorLayout, LayoutSFB: TensorLayout, AOffsetsLayout: TensorLayout, ExpertIdsLayout: TensorLayout, N: Int, K_BYTES: Int, b_cache_policy: CacheOperation = CacheOperation.ALWAYS, dram_to_lds: Bool = False, cluster_drain_sched: Bool = False, mfma_cluster: Int = Int(4), deep_prime: Bool = False, waves_per_eu: Int = Int(0)](c_tensor: TileTensor[out_dtype, LayoutC, MutAnyOrigin], a_tensor: TileTensor[DType.uint8, LayoutA, ImmutAnyOrigin], b_pre_tensor: TileTensor[DType.uint8, LayoutBPre, ImmutAnyOrigin], sfa_tensor: TileTensor[DType.float8_e8m0fnu, LayoutSFA, ImmutAnyOrigin], sfb_tensor: TileTensor[DType.float8_e8m0fnu, LayoutSFB, ImmutAnyOrigin], a_offsets: TileTensor[DType.uint32, AOffsetsLayout, ImmutAnyOrigin], expert_ids: TileTensor[DType.int32, ExpertIdsLayout, ImmutAnyOrigin], num_active_experts: Int, max_padded_M: Int)
launch
static def launch[BM: Int, BN: Int, BK_ELEMS: Int, WN: Int, persistent: Bool, b_cache_policy: CacheOperation = CacheOperation.ALWAYS, dram_to_lds: Bool = False, cluster_drain_sched: Bool = False, mfma_cluster: Int = Int(4), deep_prime: Bool = False, waves_per_eu: Int = Int(0)](c: TileTensor[Storage=c.Storage, address_space=c.address_space, linear_idx_type=c.linear_idx_type, element_size=c.element_size], a: TileTensor[DType.uint8, Storage=a.Storage, address_space=a.address_space, linear_idx_type=a.linear_idx_type, element_size=a.element_size], b_pre: TileTensor[DType.uint8, Storage=b_pre.Storage, address_space=b_pre.address_space, linear_idx_type=b_pre.linear_idx_type, element_size=b_pre.element_size], a_scales: TileTensor[DType.float8_e8m0fnu, Storage=a_scales.Storage, address_space=a_scales.address_space, linear_idx_type=a_scales.linear_idx_type, element_size=a_scales.element_size], b_scales: TileTensor[DType.float8_e8m0fnu, Storage=b_scales.Storage, address_space=b_scales.address_space, linear_idx_type=b_scales.linear_idx_type, element_size=b_scales.element_size], a_offsets: TileTensor[DType.uint32, Storage=a_offsets.Storage, linear_idx_type=a_offsets.linear_idx_type, element_size=a_offsets.element_size], expert_ids: TileTensor[DType.int32, Storage=expert_ids.Storage, linear_idx_type=expert_ids.linear_idx_type, element_size=expert_ids.element_size], max_num_tokens_per_expert: Int, num_active_experts: Int, ctx: DeviceContext)
Was this page helpful?
Thank you! We'll create more content like this.
Thank you for helping us improve!