↓ 1 callersFunctionmake_tcgen05_atom_kernel(M, N, K, in_dtype, out_dtype, accum_dtype)
testing/python/language/test_tilelang_language_atom_mma.py:245
↓ 1 callersFunctionmake_wgmma_atom_kernel(M, N, K, in_dtype, out_dtype, accum_dtype)
testing/python/language/test_tilelang_language_atom_mma.py:141
↓ 1 callersFunctionmatmu_jit_kernel(
M,
N,
K,
block_M,
block_N,
block_K,
trans_A,
trans_B,
in_dtype,
out_
testing/python/jit/test_tilelang_jit_tvm_ffi.py:55
↓ 1 callersFunctionmatmu_jit_kernel(
M,
N,
K,
block_M,
block_N,
block_K,
trans_A,
trans_B,
in_dtype,
out_
testing/python/jit/test_tilelang_jit_gemm_cython.py:55
↓ 1 callersFunctionmatmu_jit_kernel(
M,
N,
K,
block_M,
block_N,
block_K,
trans_A,
trans_B,
in_dtype,
out_
testing/python/jit/test_tilelang_jit_callback.py:125
↓ 1 callersFunctionmatmu_jit_kernel(
M,
N,
K,
block_M,
block_N,
block_K,
trans_A,
trans_B,
in_dtype,
out_
testing/python/jit/test_tilelang_jit_nvrtc.py:55
↓ 1 callersFunctionmatmul(
M,
N,
K,
block_M,
block_N,
block_K,
trans_A,
trans_B,
in_dtype,
out_
maint/gemm/correctness_evaluation_tcgen05.py:8
↓ 1 callersFunctionmatmul(
M,
N,
K,
block_M,
block_N,
block_K,
trans_A,
trans_B,
in_dtype,
out_
maint/gemm/correctness_evaluation_sm70.py:8
↓ 1 callersFunctionmatmul(
M,
N,
K,
block_M,
block_N,
block_K,
trans_A,
trans_B,
in_dtype,
out_
maint/gemm/correctness_evaluation.py:9
↓ 1 callersFunctionmatmul(
M,
N,
K,
block_M,
block_N,
block_K,
in_dtype,
out_dtype,
accum_dtype,
examples/dequantize_gemm/example_dequant_gemm_fine_grained.py:17
↓ 1 callersFunctionmatmul(A, B, block_M, block_N, block_K, dtype=T.float16, accum_dtype=T.float32)
examples/visual_layout_inference/visual_layout_inference.py:12
↓ 1 callersFunctionmatmul(A, B, block_M, block_N, block_K, dtype, accum_dtype=T.float32)
examples/gemm_fp8/example_tilelang_gemm_fp8_2xAcc.py:8
↓ 1 callersFunctionmatmul(A, B, block_M, block_N, block_K, dtype, accum_dtype=T.float32)
examples/gemm_fp8/example_tilelang_gemm_fp8.py:15
↓ 1 callersFunctionmatmul(
M,
N,
K,
block_M,
block_N,
block_K,
trans_A,
trans_B,
in_dtype,
out_
testing/python/components/test_tilelang_pass_config_disable_warp_specialized.py:6
↓ 1 callersFunctionmatmul(
M,
N,
K,
block_M,
block_N,
block_K,
trans_A,
trans_B,
in_dtype,
out_
testing/python/utils/test_compress_utils.py:12
↓ 1 callersFunctionmatmul(M, N, K, block_M, block_N, block_K, dtype=T.float16, accum_dtype=T.float32)
testing/python/profiler/test_tilelang_profiler.py:7
↓ 1 callersFunctionmatmul(
M,
N,
K,
block_M,
block_N,
block_K,
trans_A,
trans_B,
in_dtype,
out_
testing/python/language/test_tilelang_language_pipeline.py:6
↓ 1 callersFunctionmatmul(M, N, K, block_M, block_N, block_K, dtype=T.float16, accum_dtype=T.float32)
testing/python/language/test_tilelang_language_clear.py:7
↓ 1 callersFunctionmatmul(M, N, K, block_M, block_N, block_K, dtype=T.float16, accum_dtype=T.float32)
testing/python/language/test_tilelang_language_alias.py:7
↓ 1 callersFunctionmatmul(M, N, K, block_M, block_N, block_K, dtype=T.float16, accum_dtype=T.float32)
testing/python/cpu/test_tilelang_cpu_gemm.py:8
↓ 1 callersFunctionmatmul(
M,
N,
K,
block_M,
block_N,
block_K,
trans_A,
trans_B,
in_dtype,
out_
testing/python/amd/test_tilelang_test_amd.py:8
↓ 1 callersFunctionmatmul(M, N, K, block_M, block_N, block_K, dtype=T.float16, accum_dtype=T.float32)
testing/python/issue/test_tilelang_issue_96.py:7
↓ 1 callersFunctionmatmul(
M,
N,
K,
block_M,
block_N,
block_K,
trans_A,
trans_B,
in_dtype,
out_
testing/python/jit/test_tilelang_jit_callback.py:9
↓ 1 callersFunctionmatmul(M, N, K, block_M, block_N, block_K, dtype=T.float32, accum_dtype=T.float32)
testing/python/metal/test_metal_codegen_linux.py:13
↓ 1 callersFunctionmatmul(M, N, K, block_M, block_N, block_K, dtype=T.float32, accum_dtype=T.float32)
testing/python/metal/test_metal_codegen.py:9
↓ 1 callersFunctionmatmul(M, N, K, block_M, block_N, block_K, dtype=T.float16, accum_dtype=T.float32)
testing/python/webgpu/test_webgpu_codegen.py:7
↓ 1 callersFunctionmatmul(
M,
N,
K,
block_M,
block_N,
block_K,
trans_A,
trans_B,
in_dtype,
out_
testing/python/tilelibrary/test_tilelang_tilelibrary_gemm_sp.py:10
↓ 1 callersFunctionmatmul(M, N, K, block_M=128, block_N=128, block_K=32, num_stages=0, thread_num=128, enable_rasterization=False)
testing/python/autotune/test_tilelang_autotune_with_inputs.py:41
↓ 1 callersFunctionmatmul(A, B, block_M=128, block_N=128, block_K=32, num_stages=0, thread_num=128, enable_rasterization=False)
testing/python/autotune/test_tilelang_autotune_eager_mode.py:41
↓ 1 callersFunctionmatmul(
M,
N,
K,
block_M,
block_N,
block_K,
trans_A,
trans_B,
in_dtype,
out_
testing/python/kernel/test_tilelang_kernel_gemm.py:6
↓ 1 callersFunctionmatmul(M, N, K, block_M, block_N, block_K, dtype=T.float16, accum_dtype=T.float32)
testing/python/kernel/test_tilelang_kernel_gemm_with_stride.py:7
↓ 1 callersFunctionmatmul_2cta(
M,
N,
K,
block_M,
block_N,
block_K,
in_dtype,
out_dtype,
accum_dtype,
maint/gemm/correctness_evaluation_tcgen05_2cta.py:9
↓ 1 callersFunctionmatmul_batched(
batch,
M,
N,
K,
block_M,
block_N,
block_K,
trans_A,
trans_B,
in_dtyp
testing/python/kernel/test_tilelang_kernel_gemm_batched.py:6
↓ 1 callersFunctionmatmul_dynamic(M, N, K, block_M, block_N, block_K, trans_A, trans_B, in_dtype, out_dtype, accum_dtype, num_stages, threads)
examples/dynamic_shape/example_dynamic.py:54
↓ 1 callersFunctionmatmul_float_variable(
M,
N,
K,
block_M,
block_N,
block_K,
trans_A,
trans_B,
in_dtype,
out_
testing/python/jit/test_tilelang_jit_gemm_cython.py:429
↓ 1 callersFunctionmatmul_gemm_v2(M, N, K, block_M, block_N, block_K, dtype=T.float16, accum_dtype=T.float32)
testing/python/metal/test_metal_gemm_v2.py:15
↓ 1 callersFunctionmatmul_gemm_v2(M, N, K, block_M, block_N, block_K, dtype=T.float16, accum_dtype=T.float32)
testing/python/metal/test_metal_gemm_v2_linux.py:14
↓ 1 callersFunctionmatmul_int_variable(
M,
N,
K,
block_M,
block_N,
block_K,
trans_A,
trans_B,
in_dtype,
out_
testing/python/jit/test_tilelang_jit_gemm_cython.py:358
↓ 1 callersFunctionmatmul_jit_kernel(
M,
N,
K,
block_M,
block_N,
block_K,
trans_A,
trans_B,
in_dtype,
out_
testing/python/jit/test_tilelang_jit_cutedsl.py:68
↓ 1 callersFunctionmatmul_jit_test(M, N, K, block_M, block_N, block_K, dtype=T.float16, accum_dtype=T.float32)
testing/python/cpu/test_tilelang_cpu_gemm.py:64
↓ 1 callersFunctionmatmul_kernel_jit(
M,
N,
K,
block_M,
block_N,
block_K,
trans_A,
trans_B,
in_dtype,
out_
testing/python/jit/test_tilelang_jit_gemm.py:10
↓ 1 callersFunctionmatmul_nested_papipa(
M,
N,
K,
block_M,
block_N,
block_K,
in_dtype,
out_dtype,
accum_dtype,
testing/python/analysis/test_tilelang_nested_loop_checker.py:407
↓ 1 callersFunctionmatmul_nested_pipelines(
M, N, K, block_M, block_N, block_K, trans_A, trans_B, in_dtype, out_dtype, accum_dtype, threads, extra_p
testing/python/analysis/test_tilelang_nested_loop_checker.py:102
↓ 1 callersFunctionmatmul_nt(M, N, K, bM, bN, bK, in_dtype, out_dtype, accum_dtype)
testing/python/kernel/test_tilelang_kernel_int8_gemm_tcgen5.py:13
↓ 1 callersFunctionmatmul_nt_int4(M, N, K, block_M, block_N, block_K, threads=128)
examples/gemm_int4/example_tilelang_gemm_int4.py:17
↓ 1 callersFunctionmatmul_relu_kernel(
A: T.Tensor((M, K), T.float16),
B: T.Tensor((K, N), T.float16),
C: T.Tensor((M, N),
testing/python/language/test_tilelang_language_async_copy_gemm_sm80.py:26
↓ 1 callersFunctionmatmul_rr(
M,
N,
K,
block_M,
block_N,
block_K,
trans_A,
trans_B,
in_dtype,
out_
maint/gemm/correctness_evaluation.py:297
↓ 1 callersFunctionmatmul_rr(
M,
N,
K,
block_M,
block_N,
block_K,
trans_A,
trans_B,
in_dtype,
out_
testing/python/tilelibrary/test_tilelang_tilelibrary_gemm_sp.py:526
↓ 1 callersFunctionmatmul_rs(
M,
N,
K,
block_M,
block_N,
block_K,
trans_A,
trans_B,
in_dtype,
out_
maint/gemm/correctness_evaluation_sm70.py:127
↓ 1 callersFunctionmatmul_rs(
M,
N,
K,
block_M,
block_N,
block_K,
trans_A,
trans_B,
in_dtype,
out_
maint/gemm/correctness_evaluation.py:128
↓ 1 callersFunctionmatmul_rs(
M,
N,
K,
block_M,
block_N,
block_K,
trans_A,
trans_B,
in_dtype,
out_
testing/python/amd/test_tilelang_test_amd.py:147
↓ 1 callersFunctionmatmul_rs(
M,
N,
K,
block_M,
block_N,
block_K,
trans_A,
trans_B,
in_dtype,
out_
testing/python/tilelibrary/test_tilelang_tilelibrary_gemm_sp.py:189
↓ 1 callersFunctionmatmul_rs(
M,
N,
K,
block_M,
block_N,
block_K,
trans_A,
trans_B,
in_dtype,
out_
testing/python/kernel/test_tilelang_kernel_gemm.py:431
↓ 1 callersFunctionmatmul_sp_fp16(M, N, K, accum_dtype, e_dtype, block_M, block_N, block_K, num_stages, thread_num, policy, enable_rasterizatio
examples/gemm_sp/example_gemm_sp.py:13
↓ 1 callersFunctionmatmul_sr(
M,
N,
K,
block_M,
block_N,
block_K,
trans_A,
trans_B,
in_dtype,
out_
maint/gemm/correctness_evaluation.py:212
↓ 1 callersFunctionmatmul_sr(
M,
N,
K,
block_M,
block_N,
block_K,
trans_A,
trans_B,
in_dtype,
out_
testing/python/tilelibrary/test_tilelang_tilelibrary_gemm_sp.py:357
↓ 1 callersFunctionmatmul_sr(
M,
N,
K,
block_M,
block_N,
block_K,
trans_A,
trans_B,
in_dtype,
out_
testing/python/kernel/test_tilelang_kernel_gemm.py:311
↓ 1 callersFunctionmatmul_test(M, N, K, block_M, block_N, block_K, dtype=T.float16, accum_dtype=T.float32)
testing/python/language/test_tilelang_language_ptr.py:9
↓ 1 callersFunctionmatmul_tma_copy(
M,
N,
K,
block_M,
block_N,
block_K,
in_dtype,
out_dtype,
accum_dtype,
testing/python/language/test_tilelang_language_tma_copy.py:23
↓ 1 callersFunctionmatmul_with_parallel(
M,
N,
K,
block_M,
block_N,
block_K,
in_dtype,
out_dtype,
accum_dtype,
testing/python/analysis/test_tilelang_nested_loop_checker.py:526
↓ 1 callersFunctionmla_decode_triton(
q_nope,
q_pe,
kv_c_cache,
k_pe_cache,
o,
req_to_tokens,
b_seq_len,
attn_logi
examples/deepseek_mla/benchmark_mla.py:349
↓ 1 callersFunctionmla_decode_triton(
q_nope,
q_pe,
kv_c_cache,
k_pe_cache,
o,
req_to_tokens,
b_seq_len,
attn_logi
examples/deepseek_mla/amd/benchmark_mla_decode_amd_triton.py:270