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 function

enqueue_apple_matmul_clamp_chain

def enqueue_apple_matmul_clamp_chain[in_type: DType, c_type: DType = DType.float32](c: TileTensor[c_type, Storage=c.Storage, address_space=c.address_space, linear_idx_type=c.linear_idx_type], a: TileTensor[in_type, Storage=a.Storage, address_space=a.address_space, linear_idx_type=a.linear_idx_type], b: TileTensor[in_type, Storage=b.Storage, address_space=b.address_space, linear_idx_type=b.linear_idx_type], ctx: DeviceContext)

Enqueue the clamp_v2 ragged-edge, 2-pass chained-accumulate dense GEMM (NN only). Pass 0 zero-seeds and covers the first half of K's strips; pass 1 seeds from c and covers the rest, overwriting c with the final result. No partials buffer, no separate reduce kernel.

Caller guarantees c_type == float32, no elementwise_lambda_fn, transpose_b == False, m >= BM, n >= BN, and k % block_k == 0. Re-asserted here (debug_assert) since violating them walks the shifted A/B/C pointers out of their buffers' allocations.