[Bugfix] Fix Qwen3-coder moe tuned config (#24072)

Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
This commit is contained in:
Jee Jee Li
2025-09-07 05:19:46 +00:00
committed by GitHub
parent 81c53ef55c
commit 62f66be1f7
2 changed files with 48 additions and 44 deletions
+5 -1
View File
@@ -678,7 +678,11 @@ def main(args: argparse.Namespace):
is_fp16 = not (use_fp8_w8a8 or use_int8_w8a16)
search_space = get_configs_compute_bound(is_fp16, block_quant_shape)
print(f"Start tuning over {len(search_space)} configurations...")
if use_deep_gemm:
raise ValueError(
"Tuning with --use-deep-gemm is not supported as it only tunes Triton "
"kernels. Please remove the flag."
)
start = time.time()
configs = _distribute(
"tune",