@tduncan / Nvidia-Optimization-Stack-VLLM Mirror · read-only / commits / 461cde2080
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, 04:30 UTC

[OpenVINO] Fixed installation conflicts (#11458)

Signed-off-by: Ilya Lavrenov <ilya.lavrenov@intel.com>

Ilya Lavrenov committed Dec 24, 2024 at 15:38 UTC 461cde20801eb77be32227e0f23d43a6a1299b48
1 file changed +2 -2
requirements-openvino.txt
+2 -2
@@ -4,5 +4,5 @@
4 torch == 2.5.1 # should be aligned with "common" vLLM torch version
5 openvino >= 2024.4.0 # since 2024.4.0 both CPU and GPU support Paged Attention
6
7 -optimum @ git+https://github.com/huggingface/optimum.git@main # latest optimum is used to support latest transformers version
8 -optimum-intel[nncf] @ git+https://github.com/huggingface/optimum-intel.git@main # latest optimum-intel is used to support latest transformers version
7 +optimum @ git+https://github.com/huggingface/optimum.git # latest optimum is used to support latest transformers version
8 +optimum-intel[nncf] @ git+https://github.com/huggingface/optimum-intel.git # latest optimum-intel is used to support latest transformers version