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, 03:00 UTC
[BugFix] Fix tensorizer extra in setup.py (#4072)
Nick Hill committed
Apr 14, 2024 at 22:12 UTC
563c54f760f870ae44c7662c8a9ec3a223a3c4c4
1 file changed
+1
-1
setup.py
+1
-1
@@ -406,7 +406,7 @@ setup(
406
install_requires=get_requirements(),
407
ext_modules=ext_modules,
408
extras_require={
409
- "optional": ["tensorizer==2.9.0a1"],
409
+ "tensorizer": ["tensorizer==2.9.0a1"],
410
},
411
cmdclass={"build_ext": cmake_build_ext} if not _is_neuron() else {},
412
package_data=package_data,