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 58b6de8 commit 07ec941Copy full SHA for 07ec941
examples/offline_inference/long_context.py
@@ -56,7 +56,7 @@
56
trunc = args.trunc_print_len
57
58
max_num_seqs = args.max_num_seqs # defines the max batch size
59
-assert args.max_prompt_len < args.max_model_len
+assert args.max_prompt_len <= args.max_model_len
60
61
if platform.machine() == "arm64":
62
print("Detected arm64 running environment. "
@@ -122,7 +122,7 @@ def round_up(t):
122
123
124
tokens_to_generate = [
125
- args.max_model_len - round_up(plen) for plen in prompt_lens
+ args.max_model_len + 1 - round_up(plen) for plen in prompt_lens
126
]
127
128
sampling_params = [
0 commit comments