A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 3, 11:45 UTC
delete xpu ci (#42582)
Signed-off-by: wenjun.liu <wenjun.liu@intel.com> Co-authored-by: Kunshang Ji <kunshang.ji@intel.com> Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
wenjun liu committed
May 18, 2026 at 16:36 UTC
c38bed4248e97e5ed981569777d035d31ace5368
2 files changed
-60
.buildkite/hardware_tests/intel.yaml
-7
@@ -8,10 +8,3 @@ steps:
8
commands:
9
- bash .buildkite/scripts/hardware_ci/run-hpu-test.sh
10
11
- - label: "Intel GPU Test"
12
- depends_on: []
13
- soft_fail: true
14
- device: intel_gpu
15
- no_plugin: true
16
- commands:
17
- - bash .buildkite/scripts/hardware_ci/run-xpu-test.sh
.buildkite/scripts/hardware_ci/run-xpu-test.sh
deleted
-53
@@ -1,53 +0,0 @@
1
-#!/bin/bash
2
-
3
-# This script build the CPU docker image and run the offline inference inside the container.
4
-# It serves a sanity check for compilation and basic model usage.
5
-set -ex
6
-
7
-image_name="xpu/vllm-ci:${BUILDKITE_COMMIT}"
8
-container_name="xpu_${BUILDKITE_COMMIT}_$(tr -dc A-Za-z0-9 < /dev/urandom | head -c 10; echo)"
9
-
10
-# Try building the docker image
11
-docker build -t "${image_name}" -f docker/Dockerfile.xpu .
12
-
13
-# Setup cleanup
14
-remove_docker_container() {
15
- docker rm -f "${container_name}" || true
16
-}
17
-trap remove_docker_container EXIT
18
-
19
-# Run the image and test offline inference/tensor parallel
20
-docker run \
21
- --device /dev/dri:/dev/dri \
22
- --net=host \
23
- --ipc=host \
24
- --privileged \
25
- -v /dev/dri/by-path:/dev/dri/by-path \
26
- --entrypoint="" \
27
- -e "HF_TOKEN=${HF_TOKEN}" \
28
- -e "ZE_AFFINITY_MASK=${ZE_AFFINITY_MASK}" \
29
- --name "${container_name}" \
30
- "${image_name}" \
31
- bash -c '
32
- set -e
33
- echo $ZE_AFFINITY_MASK
34
- python3 examples/basic/offline_inference/generate.py --model facebook/opt-125m --block-size 64 --enforce-eager
35
- python3 examples/basic/offline_inference/generate.py --model facebook/opt-125m --block-size 64 -O3 -cc.cudagraph_mode=NONE
36
- python3 examples/basic/offline_inference/generate.py --model facebook/opt-125m --block-size 64 --enforce-eager -tp 2 --distributed-executor-backend ray
37
- python3 examples/basic/offline_inference/generate.py --model facebook/opt-125m --block-size 64 --enforce-eager -tp 2 --distributed-executor-backend mp
38
- python3 examples/basic/offline_inference/generate.py --model facebook/opt-125m --block-size 64 --enforce-eager --attention-backend=TRITON_ATTN
39
- python3 examples/basic/offline_inference/generate.py --model facebook/opt-125m --block-size 64 --enforce-eager --quantization fp8
40
- python3 examples/basic/offline_inference/generate.py --model superjob/Qwen3-4B-Instruct-2507-GPTQ-Int4 --block-size 64 --enforce-eager --max-model-len 8192
41
- python3 examples/basic/offline_inference/generate.py --model ibm-research/PowerMoE-3b --block-size 64 --enforce-eager -tp 2
42
- python3 examples/basic/offline_inference/generate.py --model ibm-research/PowerMoE-3b --block-size 64 --enforce-eager -tp 2 --enable-expert-parallel
43
- python3 examples/basic/offline_inference/generate.py --model OPEA/Qwen2.5-0.5B-Instruct-int4-sym-inc --block-size 64 --enforce-eager --max-model-len 8192
44
- cd tests
45
- pytest -v -s v1/core --ignore=v1/core/test_reset_prefix_cache_e2e.py --ignore=v1/core/test_scheduler_e2e.py
46
- pytest -v -s v1/engine
47
- pytest -v -s v1/sample --ignore=v1/sample/test_logprobs.py --ignore=v1/sample/test_logprobs_e2e.py
48
- pytest -v -s v1/worker --ignore=v1/worker/test_gpu_model_runner.py --ignore=v1/worker/test_worker_memory_snapshot.py
49
- pytest -v -s v1/structured_output
50
- pytest -v -s v1/spec_decode --ignore=v1/spec_decode/test_max_len.py --ignore=v1/spec_decode/test_tree_attention.py --ignore=v1/spec_decode/test_speculators_eagle3.py --ignore=v1/spec_decode/test_acceptance_length.py
51
- pytest -v -s v1/kv_connector/unit --ignore=v1/kv_connector/unit/test_multi_connector.py --ignore=v1/kv_connector/unit/test_example_connector.py --ignore=v1/kv_connector/unit/test_lmcache_integration.py --ignore=v1/kv_connector/unit/test_hf3fs_client.py --ignore=v1/kv_connector/unit/test_hf3fs_connector.py --ignore=v1/kv_connector/unit/test_hf3fs_metadata_server.py
52
- pytest -v -s v1/test_serial_utils.py
53
-'