We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
1 parent d3d8d08 commit 22a626fCopy full SHA for 22a626f
1 file changed
diffulex_bench/configs/llada2_mini_gsm8k.yml
@@ -18,7 +18,7 @@ engine:
18
deepep_mode: "normal"
19
gpu_memory_utilization: 0.5
20
max_model_len: 4096
21
- max_num_batched_tokens: 2048
+ max_num_batched_tokens: 4096
22
max_num_reqs: 1
23
24
enforce_eager: false
0 commit comments