Mojo function

mla_decoding_single_batch

mla_decoding_single_batch[q_type: DType, k_t: MHAOperand, output_type: DType, mask_t: MHAMask, *, BM: Int, BN: Int, BK: Int, WM: Int, WN: Int, depth: Int, depth_v: Int, num_threads: Int, num_pipeline_stages: Int, decoding_warp_split_k: Bool = False](q_ptr: UnsafePointer[Scalar[q_type], MutAnyOrigin], k: k_t, output_ptr: UnsafePointer[Scalar[output_type], MutAnyOrigin], exp_sum_ptr: UnsafePointer[Scalar[get_accum_type[q_type]()], MutAnyOrigin], qk_max_ptr: UnsafePointer[Scalar[get_accum_type[q_type]()], MutAnyOrigin], scale: Float32, num_keys: Int, num_partitions: Int, mask: mask_t, batch_idx: Int)

Flash attention v2 algorithm.

Was this page helpful?

Thank you! We'll create more content like this.

Thank you for helping us improve!

😔 What went wrong?

Some code doesn’t work

It includes inaccurate information

It's missing information I need

It was difficult to understand

Other

Submit