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