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 10, 12:45 UTC
[platform] add dp_metadata arg to set_additional_forward_context (#31942)
Signed-off-by: Ronald1995 <ronaldautomobile@163.com>
Ronald committed
Jan 8, 2026 at 14:56 UTC
2ab441befef05b3c5ffdb23f981f13d035f4cd3c
1 file changed
+1
vllm/forward_context.py
+1
@@ -319,6 +319,7 @@ def set_forward_context(
319
attn_metadata=attn_metadata,
320
vllm_config=vllm_config,
321
virtual_engine=virtual_engine,
322
+ dp_metadata=dp_metadata,
323
num_tokens=num_tokens,
324
num_tokens_across_dp=num_tokens_across_dp,
325
cudagraph_runtime_mode=cudagraph_runtime_mode,