8000 Bugfix: n_batch should always be <= n_ctx · coderonion/llama-cpp-python@5075c16 · GitHub
[go: up one dir, main page]

Skip to content

Commit 5075c16

Browse files
committed
Bugfix: n_batch should always be <= n_ctx
1 parent 248b056 commit 5075c16

File tree

1 file changed

+1
-1
lines changed

1 file changed

+1
-1
lines changed

llama_cpp/llama.py

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -68,7 +68,7 @@ def __init__(
6868
maxlen=self.last_n_tokens_size,
6969
)
7070
self.tokens_consumed = 0
71-
self.n_batch = n_batch
71+
self.n_batch = min(n_ctx, n_batch)
7272

7373
self.n_threads = n_threads or multiprocessing.cpu_count()
7474

0 commit 307D comments

Comments
 (0)
0