A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 8, 05:00 UTC
Fix docs build warning (#34686)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Harry Mellor committed
Feb 17, 2026 at 10:31 UTC
28bffe9466aeea56b7301e1d27c2cb7e18dcbc15
1 file changed
-1
vllm/v1/worker/gpu/pp_handler.py
-1
@@ -70,7 +70,6 @@ class PPHandler:
70
71
Args:
72
num_reqs: Number of requests in the batch.
73
- device: Device to create tensors on.
73
max_sample_len: Maximum number of tokens sampled per request
74
(1 for regular decode, >1 for speculative decoding).
75