Gahow Wang
445e491123
third_party/vllm/ now tracked in git for direct patch management.
Based on vLLM v0.18.1 release with one patch applied:
vllm/v1/core/sched/scheduler.py:
Replace fatal assert with graceful skip when KV transfer callback
arrives for an already-aborted request during PD disaggregated serving.
Future vLLM modifications should be made directly in third_party/vllm/
and committed normally. The patches/ directory is kept as documentation
of what changed from upstream.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
14 lines
427 B
Bash
Executable File
14 lines
427 B
Bash
Executable File
#!/bin/bash
|
|
|
|
# This script build the CPU docker image and run the offline inference inside the container.
|
|
# It serves a sanity check for compilation and basic model usage.
|
|
set -ex
|
|
|
|
# Setup cleanup
|
|
remove_docker_container() { docker rm -f cpu-test || true; docker system prune -f; }
|
|
trap remove_docker_container EXIT
|
|
remove_docker_container
|
|
|
|
# Try building the docker image
|
|
docker build -t cpu-test -f docker/Dockerfile.s390x .
|