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 12, 09:45 UTC
[compile] Include `enable_sleep_mode` into caching factors. (#29696)
Signed-off-by: zhxchen17 <zhxchen17@fb.com>
Zhengxu Chen committed
Nov 28, 2025 at 18:58 UTC
6173682b6e98ae62f612db7af6813831097b23dc
1 file changed
-1
vllm/config/model.py
-1
@@ -353,7 +353,6 @@ class ModelConfig:
353
"hf_token",
354
"hf_overrides",
355
"logits_processor_pattern",
356
- "enable_sleep_mode",
356
"override_attention_dtype",
357
"logits_processors",
358
"io_processor_plugin",