Unverified Commit 5d134401 authored by Zhaoyang Hao's avatar Zhaoyang Hao Committed by GitHub
Browse files

[FIX] Fix concatenation error in capture_bs when open...

[FIX] Fix concatenation error in capture_bs when open --disable-cuda-graph-padding and without MTP (#5412)
parent f88f7e19
......@@ -116,7 +116,7 @@ def get_batch_sizes_to_capture(model_runner: ModelRunner):
if capture_bs is None:
if server_args.speculative_algorithm is None:
if server_args.disable_cuda_graph_padding:
capture_bs = list(range(1, 33)) + range(40, 161, 16)
capture_bs = list(range(1, 33)) + list(range(40, 161, 16))
else:
capture_bs = [1, 2, 4, 8] + list(range(16, 161, 8))
else:
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment