From 4b502a62ed7b2dba983cd89eef3eb4bfef036f88 Mon Sep 17 00:00:00 2001 From: Marcin Swiniarski Date: Mon, 2 Dec 2024 17:03:47 +0100 Subject: [PATCH] Set vllm-hpu-extension to fb36408 (#572) Set vllm-hpu-extension to fb36408, that includes support for non-GQA workloads in PipelinedPA --- requirements-hpu.txt | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/requirements-hpu.txt b/requirements-hpu.txt index da2896bef70de..91c73d0a70db0 100644 --- a/requirements-hpu.txt +++ b/requirements-hpu.txt @@ -8,5 +8,5 @@ pandas tabulate setuptools>=61 setuptools-scm>=8 -vllm-hpu-extension @ git+https://github.com/HabanaAI/vllm-hpu-extension.git@bc01901 +vllm-hpu-extension @ git+https://github.com/HabanaAI/vllm-hpu-extension.git@fb36408 neural-compressor @ git+https://github.com/intel/neural-compressor.git@b196432