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 17, 01:45 UTC
[CI/Build][Bugfix] VLLM_USE_PRECOMPILED should skip compilation (#4534)
Signed-off-by: Travis Johnson <tsjohnso@us.ibm.com>
Travis Johnson committed
May 1, 2024 at 12:01 UTC
8b798eec75cde6eb6fe65b5d673dd9bd4eaef799
1 file changed
+1
setup.py
+1
@@ -378,6 +378,7 @@ package_data = {
378
"vllm": ["py.typed", "model_executor/layers/fused_moe/configs/*.json"]
379
}
380
if os.environ.get("VLLM_USE_PRECOMPILED"):
381
+ ext_modules = []
382
package_data["vllm"].append("*.so")
383
384
setup(