Refactor tuning block wise kernel and opt Qwen/Qwen3-VL-32B-Instruct-FP8 (#14141)

This commit is contained in:
Xiaoyu Zhang
2025-12-08 09:24:58 +08:00
committed by GitHub
parent aff1238ef2
commit 03b835e7d1
8 changed files with 334 additions and 64 deletions

View File

@@ -84,6 +84,8 @@ def w8a8_block_matmul(
C_shape = A.shape[:-1] + (N,)
C = A.new_empty(C_shape, dtype=output_dtype)
needs_masking = bool(K % config["BLOCK_SIZE_K"] != 0)
def grid(META):
return (
triton.cdiv(M, META["BLOCK_SIZE_M"]) * triton.cdiv(N, META["BLOCK_SIZE_N"]),
@@ -127,6 +129,7 @@ def w8a8_block_matmul(
Bs.stride(1),
Bs.stride(0),
**config,
needs_masking=needs_masking,
)
return C
@@ -428,7 +431,13 @@ def main(args):
batch_sizes = [args.batch_size]
num_gpus = 1 # If only one batch size, use only one GPU
weight_shapes = get_weight_shapes(args.tp_size)
# Support manual N and K specification
if args.N is not None and args.K is not None:
weight_shapes = [(args.N, args.K)]
print(f"Using manually specified weight shape: N={args.N}, K={args.K}")
else:
weight_shapes = get_weight_shapes(args.tp_size)
print(f"Using predefined weight shapes for TP size {args.tp_size}")
batches_per_gpu = distribute_batch_sizes(batch_sizes, num_gpus)
@@ -453,7 +462,25 @@ def main(args):
if __name__ == "__main__":
parser = argparse.ArgumentParser()
parser.add_argument("--tp-size", "-tp", type=int, default=8)
parser.add_argument(
"--tp-size",
"-tp",
type=int,
default=8,
help="Tensor parallelism size (ignored if --N and --K are specified)",
)
parser.add_argument(
"--N",
type=int,
default=None,
help="Output dimension of weight matrix (number of columns)",
)
parser.add_argument(
"--K",
type=int,
default=None,
help="Input dimension of weight matrix (number of rows)",
)
parser.add_argument(
"--input-type", type=str, choices=["fp8", "int8"], default="fp8"
)
@@ -471,4 +498,8 @@ if __name__ == "__main__":
)
args = parser.parse_args()
# Validate arguments
if (args.N is None) != (args.K is None):
parser.error("--N and --K must be specified together or not at all")
main(args)