↓ 1 callersFunctiontensor_null_test(M, N, K, block_M, block_N, block_K, dtype=T.float16, accum_dtype=T.float32, with_bias=False)
testing/python/jit/test_tilelang_jit_nullptr.py:9
↓ 1 callersFunctiontest_convert(N, K, block_N, block_K, in_dtype, num_bits=4, threads=128)
examples/dequantize_gemm/example_dequant_gemm_fp4_hopper.py:45
↓ 1 callersFunctiontest_correctness(
BATCH: int = 1,
H: int = 8,
N_CTX: int = 512,
N_KV: int = 1024,
D_HEAD: int = 128,
T
examples/deepseek_v4/sparse_attn_fwd_sm90.py:190
↓ 1 callersFunctiontest_kernel(
B=1,
S=2048,
H=16,
D=512,
tail_D=64,
index_D=128,
topk=64,
)
examples/dsa_sparse_finetune/dsa.py:166
↓ 1 callersFunctiontest_kernel(
B=1,
S=2048,
H=16,
D=512,
tail_D=64,
topk=128,
)
examples/dsa_sparse_finetune/sparse_mla_topk_reducesum.py:201
↓ 1 callersFunctiontest_sparse_mla_bwd(B=1, S=4096, SKV=8192, H=64, HKV=1, DQKV=576, DV=512, topk=2048, dtype=torch.bfloat16, check_correctness=True
examples/deepseek_v32/sparse_mla_bwd.py:282
↓ 1 callersFunctiontest_sparse_mla_bwd(B=1, S=2048, H=64, HKV=1, DQKV=576, DV=512, topk=512, dtype=torch.bfloat16, check_correctness=True)
examples/dsa_sparse_finetune/sparse_mla_bwd.py:293
↓ 1 callersFunctiontest_sparse_mla_fwd(
B=1,
S=4096,
SKV=8192,
H=128,
HKV=1,
DQK=576,
DV=512,
topk=2048,
dtype=t
examples/deepseek_v32/sparse_mla_fwd.py:230
↓ 1 callersFunctiontest_sparse_mla_fwd(
B=1,
S=4096,
H=128,
HKV=1,
DQK=576,
DV=512,
topk=2048,
dtype=torch.bfloat16,
examples/dsa_sparse_finetune/sparse_mla_fwd.py:260