Functiongemm_kernel(
A: T.Tensor((M, K), dtype),
B: T.Tensor((K, N), dtype),
C: T.Tensor((M, N), accum_dt
testing/python/metal/test_metal_gemm_v2.py:17
Functiongemm_kernel(
A: T.Tensor((M, K), dtype),
B: T.Tensor((K, N), dtype),
C: T.Tensor((M, N), accum_dt
testing/python/metal/test_metal_simdgroup_store.py:18
Functiongemm_lower(
gemm,
layout_map,
target: Target,
thread_bounds: Range,
thread_var: tirx.Var,
mbar_p
tilelang/tileop/gemm/__init__.py:19
Functiongemm_persistent(
A,
B,
block_M,
block_N,
store_block_N, # block_N for C_shared
block_K,
in_dtype
examples/gemm_sm100/gemm_tcgen5mma_ws_persistent.py:11
Functiongemm_persistent_2cta(
A,
B,
block_M,
block_N,
store_block_N, # block_N for C_shared
block_K,
in_dtype
examples/gemm_sm100/gemm_tcgen5mma_ws_persistent.py:134
Functiongemm_sp_fp16(
A_sparse: T.Tensor((M, K // 2), T.float16),
E: T.Tensor((M, K // e_factor), e_dtype),
examples/gemm_sp/example_gemm_sp.py:17
Functiongemm_swizzled(
A: T.Buffer((M, K), "float16"),
B: T.Buffer((K, N), "float16"),
C: T.Buffer((M, N),
testing/python/transform/test_tilelang_transform_producer_consumer_ws.py:450
Functiongemv_alloc_reducer(
a, x, block_M=128, block_N=128, num_stages=2, threads=256, dtype: T.dtype = T.float16, accum_dtype: T.dt
examples/gemv/example_gemv.py:230