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 11, 08:45 UTC
[compile] Ignore VLLM_FORCE_AOT_LOAD from cache factors (#30809)
Signed-off-by: zhxchen17 <zhxchen17@fb.com>
Zhengxu Chen committed
Dec 17, 2025 at 04:56 UTC
9db1db5949f7abd4b03cd0231450f81bfeeaba0f
1 file changed
+1
vllm/envs.py
+1
@@ -1654,6 +1654,7 @@ def compile_factors() -> dict[str, object]:
1654
"VLLM_CI_USE_S3",
1655
"VLLM_MODEL_REDIRECT_PATH",
1656
"VLLM_HOST_IP",
1657
+ "VLLM_FORCE_AOT_LOAD",
1658
"S3_ACCESS_KEY_ID",
1659
"S3_SECRET_ACCESS_KEY",
1660
"S3_ENDPOINT_URL",