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 15, 08:30 UTC
[Build] fix cpu build missing libtbbmalloc.so (#18744)
Signed-off-by: Kebe <mail@kebe7jun.com>
Kebe committed
May 27, 2025 at 16:03 UTC
e0f0ff87b89978d1d0bea2aec2d85cec72b71238
1 file changed
+1
-1
requirements/cpu.txt
+1
-1
@@ -22,5 +22,5 @@ datasets # for benchmark scripts
22
triton==3.2.0; platform_machine == "x86_64"
23
24
# Intel Extension for PyTorch, only for x86_64 CPUs
25
-intel-openmp; platform_machine == "x86_64"
25
+intel-openmp==2024.2.1; platform_machine == "x86_64"
26
intel_extension_for_pytorch==2.7.0; platform_machine == "x86_64"