[CI] intel CI: add quantization and awq case for xpu (#46456)

Signed-off-by: wenjun.liu <wenjun.liu@intel.com>
Signed-off-by: zengxian <xiangdong.zeng@intel.com>
Co-authored-by: zengxian <xiangdong.zeng@intel.com>
This commit is contained in:
wenjun liu
2026-07-03 09:51:56 +08:00
committed by GitHub
co-authored by zengxian
parent 4c3c64fcf7
commit 34bf7b45a0
3 changed files with 30 additions and 0 deletions
+28
View File
@@ -0,0 +1,28 @@
group: Quantization
depends_on:
- image-build-xpu
steps:
- label: Quantization
key: quantization
timeout_in_minutes: 30
env:
REGISTRY: "public.ecr.aws/q9t5s3a7"
REPO: "vllm-ci-test-repo"
VLLM_TEST_DEVICE: "xpu"
no_plugin: true
working_dir: "."
device: intel_gpu
agent_tags:
label: production
gpu: 1+
mem: 16+
source_file_dependencies:
- csrc/
- vllm/model_executor/layers/quantization
- tests/quantization
commands:
# - VLLM_TEST_FORCE_LOAD_FORMAT=auto pytest -v -s quantization/ --ignore quantization/test_blackwell_moe.py
- >-
bash .buildkite/scripts/hardware_ci/run-intel-test.sh
'VLLM_TEST_FORCE_LOAD_FORMAT=auto pytest -v -s tests/quantization/test_per_token_kv_cache.py --deselect="tests/quantization/test_per_token_kv_cache.py::test_triton_unified_attention_per_token_head_scale[int4-16-128-num_heads0-seq_lens1]"'
+1
View File
@@ -42,6 +42,7 @@ steps:
python3 examples/basic/offline_inference/generate.py --model facebook/opt-125m --block-size 64 --enforce-eager --kv-cache-dtype fp8 &&
python3 examples/basic/offline_inference/generate.py --model nvidia/Llama-3.1-8B-Instruct-FP8 --block-size 64 --enforce-eager --quantization modelopt --kv-cache-dtype fp8 --attention-backend TRITON_ATTN --max-model-len 4096 &&
python3 examples/basic/offline_inference/generate.py --model superjob/Qwen3-4B-Instruct-2507-GPTQ-Int4 --block-size 64 --enforce-eager --max-model-len 8192 &&
python3 examples/basic/offline_inference/generate.py --model TheBloke/TinyLlama-1.1B-Chat-v0.3-AWQ --block-size 64 --enforce-eager &&
python3 examples/basic/offline_inference/generate.py --model ibm-research/PowerMoE-3b --block-size 64 --enforce-eager -tp 2 &&
python3 examples/basic/offline_inference/generate.py --model ibm-research/PowerMoE-3b --block-size 64 --enforce-eager -tp 2 --enable-expert-parallel &&
python3 examples/basic/offline_inference/generate.py --model superjob/Qwen3-4B-Instruct-2507-GPTQ-Int4 --max-model-len 8192 &&
@@ -21,6 +21,7 @@ case "${test_suite}" in
python3 examples/basic/offline_inference/generate.py --model facebook/opt-125m --block-size 64 --enforce-eager --kv-cache-dtype fp8
python3 examples/basic/offline_inference/generate.py --model nvidia/Llama-3.1-8B-Instruct-FP8 --block-size 64 --enforce-eager --quantization modelopt --kv-cache-dtype fp8 --attention-backend TRITON_ATTN --max-model-len 4096
python3 examples/basic/offline_inference/generate.py --model superjob/Qwen3-4B-Instruct-2507-GPTQ-Int4 --block-size 64 --enforce-eager --max-model-len 8192
python3 examples/basic/offline_inference/generate.py --model TheBloke/TinyLlama-1.1B-Chat-v0.3-AWQ --block-size 64 --enforce-eager
python3 examples/basic/offline_inference/generate.py --model ibm-research/PowerMoE-3b --block-size 64 --enforce-eager -tp 2
python3 examples/basic/offline_inference/generate.py --model ibm-research/PowerMoE-3b --block-size 64 --enforce-eager -tp 2 --enable-expert-parallel
python3 examples/basic/offline_inference/generate.py --model superjob/Qwen3-4B-Instruct-2507-GPTQ-Int4 --max-model-len 8192