From 2f9ededd619088ee7f4360ad25674ac06a6637a8 Mon Sep 17 00:00:00 2001 From: Vinay Damodaran Date: Thu, 22 May 2025 09:16:41 -0700 Subject: [PATCH 1/2] Update to latest CUDA version and Ubuntu version --- Dockerfile-cuda | 4 ++-- Dockerfile-cuda-all | 4 ++-- 2 files changed, 4 insertions(+), 4 deletions(-) diff --git a/Dockerfile-cuda b/Dockerfile-cuda index 537ad59f..3e29919b 100644 --- a/Dockerfile-cuda +++ b/Dockerfile-cuda @@ -1,4 +1,4 @@ -FROM nvidia/cuda:12.2.0-devel-ubuntu22.04 AS base-builder +FROM nvidia/cuda:12.8.0-devel-ubuntu24.04 AS base-builder ENV SCCACHE=0.10.0 ENV RUSTC_WRAPPER=/usr/local/bin/sccache @@ -113,7 +113,7 @@ RUN --mount=type=secret,id=actions_results_url,env=ACTIONS_RESULTS_URL \ cargo build --release --bin text-embeddings-router -F candle-cuda -F static-linking -F grpc --no-default-features && sccache -s; \ fi; -FROM nvidia/cuda:12.2.0-base-ubuntu22.04 AS base +FROM nvidia/cuda:12.8.0-base-ubuntu24.04 AS base ARG DEFAULT_USE_FLASH_ATTENTION=True diff --git a/Dockerfile-cuda-all b/Dockerfile-cuda-all index 5dca432a..4110fcea 100644 --- a/Dockerfile-cuda-all +++ b/Dockerfile-cuda-all @@ -1,4 +1,4 @@ -FROM nvidia/cuda:12.2.0-devel-ubuntu22.04 AS base-builder +FROM nvidia/cuda:12.8.0-devel-ubuntu24.04 AS base-builder ENV SCCACHE=0.10.0 ENV RUSTC_WRAPPER=/usr/local/bin/sccache @@ -124,7 +124,7 @@ RUN --mount=type=secret,id=actions_results_url,env=ACTIONS_RESULTS_URL \ RUN mv /usr/src/target/release/text-embeddings-router /usr/src/target/release/text-embeddings-router-90 -FROM nvidia/cuda:12.2.0-runtime-ubuntu22.04 AS base +FROM nvidia/cuda:12.8.0-runtime-ubuntu24.04 AS base ARG DEFAULT_USE_FLASH_ATTENTION=True From 9721c2343c5f545eb5f7da7e7be74daf143f0cf0 Mon Sep 17 00:00:00 2001 From: Vinay Damodaran Date: Tue, 3 Jun 2025 11:18:49 -0700 Subject: [PATCH 2/2] Revert CUDA version upgrade --- Dockerfile-cuda | 4 ++-- Dockerfile-cuda-all | 4 ++-- 2 files changed, 4 insertions(+), 4 deletions(-) diff --git a/Dockerfile-cuda b/Dockerfile-cuda index 3e29919b..365f0fa0 100644 --- a/Dockerfile-cuda +++ b/Dockerfile-cuda @@ -1,4 +1,4 @@ -FROM nvidia/cuda:12.8.0-devel-ubuntu24.04 AS base-builder +FROM nvidia/cuda:12.2.0-devel-ubuntu24.04 AS base-builder ENV SCCACHE=0.10.0 ENV RUSTC_WRAPPER=/usr/local/bin/sccache @@ -113,7 +113,7 @@ RUN --mount=type=secret,id=actions_results_url,env=ACTIONS_RESULTS_URL \ cargo build --release --bin text-embeddings-router -F candle-cuda -F static-linking -F grpc --no-default-features && sccache -s; \ fi; -FROM nvidia/cuda:12.8.0-base-ubuntu24.04 AS base +FROM nvidia/cuda:12.2.0-base-ubuntu24.04 AS base ARG DEFAULT_USE_FLASH_ATTENTION=True diff --git a/Dockerfile-cuda-all b/Dockerfile-cuda-all index 4110fcea..79b7fc6c 100644 --- a/Dockerfile-cuda-all +++ b/Dockerfile-cuda-all @@ -1,4 +1,4 @@ -FROM nvidia/cuda:12.8.0-devel-ubuntu24.04 AS base-builder +FROM nvidia/cuda:12.2.0-devel-ubuntu24.04 AS base-builder ENV SCCACHE=0.10.0 ENV RUSTC_WRAPPER=/usr/local/bin/sccache @@ -124,7 +124,7 @@ RUN --mount=type=secret,id=actions_results_url,env=ACTIONS_RESULTS_URL \ RUN mv /usr/src/target/release/text-embeddings-router /usr/src/target/release/text-embeddings-router-90 -FROM nvidia/cuda:12.8.0-runtime-ubuntu24.04 AS base +FROM nvidia/cuda:12.2.0-runtime-ubuntu24.04 AS base ARG DEFAULT_USE_FLASH_ATTENTION=True