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 14, 05:30 UTC
[Build] Env var to disable sccache (#22968)
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Lucas Wilkinson committed
Aug 16, 2025 at 01:36 UTC
5157827cfc0fd06d361897b2cc912ee1b5bc6277
1 file changed
+2
-1
setup.py
+2
-1
@@ -60,7 +60,8 @@ MAIN_CUDA_VERSION = "12.8"
60
61
62
def is_sccache_available() -> bool:
63
- return which("sccache") is not None
63
+ return which("sccache") is not None and \
64
+ not bool(int(os.getenv("VLLM_DISABLE_SCCACHE", "0")))
65
66
67
def is_ccache_available() -> bool: