Fix nightly (#5413)
### What this PR does / why we need it?
This pacth mainly do the following things:
1. Bugfix for multi_node_tests log, log names must be unique when
uploading logs.
2. Optimize `get_cluster_ips` logic, increase the max retry times for
robustness
3. Abandoned the existing gh-proxy temporarily until it is stable
enough.
### Does this PR introduce _any_ user-facing change?
### How was this patch tested?
- vLLM version: release/v0.13.0
- vLLM main:
81786c8774
---------
Signed-off-by: wangli <wangli858794774@gmail.com>
This commit is contained in:
@@ -24,7 +24,7 @@ def temp_env(env_dict):
|
||||
os.environ[k] = v
|
||||
|
||||
|
||||
def dns_resolver(retries: int = 20, base_delay: float = 0.5):
|
||||
def dns_resolver(retries: int = 240, base_delay: float = 0.5):
|
||||
# We should resolve DNS with retries to avoid transient network issues.
|
||||
# When the pod is just started, DNS resolution may fail.
|
||||
def resolve(dns: str):
|
||||
|
||||
@@ -13,7 +13,8 @@ LOG_DIR="/root/.cache/tests/logs"
|
||||
OVERWRITE_LOGS=true
|
||||
export LD_LIBRARY_PATH=/usr/local/Ascend/ascend-toolkit/latest/python/site-packages:$LD_LIBRARY_PATH
|
||||
export BENCHMARK_HOME=${WORKSPACE}/vllm-ascend/benchmark
|
||||
export VLLM_LOGGING_LEVEL="DEBUG"
|
||||
export VLLM_LOGGING_LEVEL="INFO"
|
||||
export TRANSFORMERS_OFFLINE="1"
|
||||
|
||||
# Function to print section headers
|
||||
print_section() {
|
||||
@@ -88,7 +89,9 @@ check_npu_info() {
|
||||
|
||||
check_and_config() {
|
||||
echo "====> Configure mirrors and git proxy"
|
||||
git config --global url."https://gh-proxy.test.osinfra.cn/https://github.com/".insteadOf "https://github.com/"
|
||||
# Fix me(Potabk): Currently, there have some issues with accessing GitHub via https://gh-proxy.test.osinfra.cn in certain regions.
|
||||
# We should switch to a more stable proxy for now until the network proxy is stable enough.
|
||||
git config --global url."https://ghfast.top/https://github.com/".insteadOf "https://github.com/"
|
||||
pip config set global.index-url https://mirrors.tuna.tsinghua.edu.cn/pypi/web/simple
|
||||
export PIP_EXTRA_INDEX_URL=https://mirrors.huaweicloud.com/ascend/repos/pypi
|
||||
}
|
||||
|
||||
@@ -114,7 +114,7 @@ async def test_multi_node() -> None:
|
||||
proxy_port=proxy_port,
|
||||
disaggregated_prefill=disaggregated_prefill,
|
||||
nodes_info=nodes_info,
|
||||
max_wait_seconds=1200,
|
||||
max_wait_seconds=2800,
|
||||
) as remote_server:
|
||||
if config.is_master:
|
||||
port = proxy_port if disaggregated_prefill else server_port
|
||||
|
||||
Reference in New Issue
Block a user