@tduncan / Nvidia-Optimization-Stack-VLLM Mirror · read-only / commits / 1a36287b89
Fork 0

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 16, 18:15 UTC

[Bugfix] Fix xpu build (#7644)

Kunshang Ji committed Aug 19, 2024 at 13:00 UTC 1a36287b89f337057ebeb5d1bee30567e985b444
1 file changed +1 -1
setup.py
+1 -1
@@ -279,7 +279,7 @@ def _build_custom_ops() -> bool:
279
280
281 def _build_core_ext() -> bool:
282 - return not _is_neuron() and not _is_tpu() and not _is_openvino()
282 + return not (_is_neuron() or _is_tpu() or _is_openvino() or _is_xpu())
283
284
285 def get_hipcc_rocm_version():