↓ 1 callersFunctionmain(
A: T.Tensor((M, K), T.float4_e2m1fn),
B: T.Tensor((N, K), T.float8_e4m3fn),
D: T.Ten
maint/gemm/correctness_evaluation_tcgen05_fp4_unpacked.py:28
↓ 1 callersFunctionmain(
A: T.Tensor((M, K), dtype),
B: T.Tensor((N, K), dtype),
C: T.Tensor((M,
examples/gemm/example_gemm_autotune.py:129
↓ 1 callersFunctionmain(
A: T.Tensor((M, K), dtype),
B: T.Tensor((N, K), dtype),
C: T.Tensor((M,
examples/gemm/example_gemm_advanced_autotune.py:184
↓ 1 callersFunctionmain(batch=1, heads=1, seq_len=4096, head_dim=64, vertical_size=1000, slash_size=200)
examples/minference/example_vertical_slash_sparse_attn.py:561
↓ 1 callersFunctionmain(
A: T.Tensor(A_shape, in_dtype),
B: T.Tensor(B_shape, storage_dtype),
C: T.Tensor((M,
examples/dequantize_gemm/example_dequant_gemm_fine_grained.py:47
↓ 1 callersFunctionmain(
B: T.Tensor(B_shape, storage_dtype),
C: T.Tensor((N, K), in_dtype),
)
examples/dequantize_gemm/example_dequant_gemm_fp4_hopper.py:53
↓ 1 callersFunctionmain(
B: T.Tensor(B_shape, storage_dtype),
C: T.Tensor((N, K), in_dtype),
)
examples/dequantize_gemm/example_dequant_gemm_w4a8.py:44
↓ 1 callersFunctionmain(
Q: T.Tensor(q_shape, dtype),
K: T.Tensor(kv_shape, dtype),
V: T.Tensor(kv_shape, dty
examples/amd/example_amd_flash_attn_bwd.py:120
↓ 1 callersFunctionmain(
Q: T.Tensor(q_shape, dtype),
K: T.Tensor(kv_shape, dtype),
V: T.Tensor(kv_shape, dty
examples/amd/example_amd_flash_attn_fwd.py:138
↓ 1 callersFunctionmain(BATCH=1, H=32, Q_CTX=128, KV_CTX=8192, D_HEAD=128, causal=False)
examples/flash_decoding/example_mha_inference.py:239
↓ 1 callersFunctionmain(batch: int = 1, heads: int = 32, groups: int = 8, kv_seqlen: int = 8192, dim: int = 128, tune: bool = False)
examples/flash_decoding/example_gqa_decode.py:403
↓ 1 callersFunctionmain(
Q: T.Tensor(shape, dtype),
K: T.Tensor(shape, dtype),
V: T.Tensor(shape, dtype),
examples/flash_attention/example_mha_fwd_bshd.py:30
↓ 1 callersFunctionmain(
BATCH: int = 8,
H: int = 32,
N_CTX: int = 1024,
D_HEAD: int = 64,
causal: bool = False,
examples/flash_attention/example_mha_bwd_bhsd.py:301
↓ 1 callersFunctionmain(
Q: T.Tensor(q_shape, dtype),
K: T.Tensor(kv_shape, dtype),
V: T.Tensor(kv_shape, dty
examples/flash_attention/example_gqa_fwd_bshd.py:77