We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
There was an error while loading. Please reload this page.
1 parent d682c97 commit e79a1a7Copy full SHA for e79a1a7
benchmarks/yaml/x1-a3b-128k-wint8-h800-tp1.yaml
@@ -1,6 +1,6 @@
1
-or_parallel_size: 1
+tensor_parallel_size: 1
2
max_model_len: 131072
3
max_num_seqs: 32
4
-quantization: wint8
5
reasoning_parser: ernie_x1
6
tool_call_parser: ernie_x1
+load_choices: "default_v1"
0 commit comments