Trying to avoid the random timeout. (#2929)

* Trying to avoid the random timeout. * More read timeout ? * Longer timeout ? * Remove legacy ENV directive. * Remove the dummy test, only increase the read timeout. * Wat?
huggingface · Jan 21, 2025 · bdb3e48 · bdb3e48
1 parent 1736743
commit bdb3e48
Show file tree

Hide file tree

Showing 2 changed files with 3 additions and 2 deletions.
diff --git a/Dockerfile b/Dockerfile
@@ -58,7 +58,7 @@ ARG INSTALL_CHANNEL=pytorch
 # Automatically set by buildx
 ARG TARGETPLATFORM
 
-ENV PATH /opt/conda/bin:$PATH
+ENV PATH=/opt/conda/bin:$PATH
 
 RUN apt-get update && DEBIAN_FRONTEND=noninteractive apt-get install -y --no-install-recommends \
         build-essential \

diff --git a/integration-tests/conftest.py b/integration-tests/conftest.py
@@ -562,6 +562,7 @@ def docker_launcher(
                 docker.types.DeviceRequest(count=gpu_count, capabilities=[["gpu"]])
             ]
 
+        client.api.timeout = 1000
         container = client.containers.run(
             DOCKER_IMAGE,
             command=args,
@@ -573,7 +574,7 @@ def docker_launcher(
             devices=devices,
             volumes=volumes,
             ports={"80/tcp": port},
-            healthcheck={"timeout": int(60 * 1e9), "retries": 2},  # 60s
+            healthcheck={"timeout": int(180 * 1e9), "retries": 2},  # 60s
             shm_size="1G",
         )