biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[Examples][1/n] Resettle basic examples. (#35579)

Browse Source 
Signed-off-by: wang.yuqi <yuqi.wang@daocloud.io>
Signed-off-by: wang.yuqi <noooop@126.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
This commit is contained in:
wang.yuqi
2026-03-09 11:22:53 +08:00
committed by GitHub
parent 43aa389231
commit dcf8862fd4
26 changed files with 64 additions and 65 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
.buildkite/scripts/hardware_ci/run-cpu-test-arm.sh
View File

@@ -34,7 +34,7 @@ function cpu_tests() {
# offline inference
docker exec cpu-test bash -c "
set -e
python3 examples/offline_inference/basic/generate.py --model facebook/opt-125m"
python3 examples/basic/offline_inference/generate.py --model facebook/opt-125m"
# Run model tests
docker exec cpu-test bash -c "

2
.buildkite/scripts/hardware_ci/run-cpu-test-ppc64le.sh
View File

@@ -27,7 +27,7 @@ function cpu_tests() {
podman exec -it "$container_id" bash -c "
export TORCH_COMPILE_DISABLE=1
set -xve
python3 examples/offline_inference/basic/generate.py --model facebook/opt-125m" >> "$HOME"/test_basic.log
python3 examples/basic/offline_inference/generate.py --model facebook/opt-125m" >> "$HOME"/test_basic.log
# Run basic model test
podman exec -it "$container_id" bash -c "

2
.buildkite/scripts/hardware_ci/run-gh200-test.sh
View File

@@ -25,5 +25,5 @@ remove_docker_container
# Run the image and test offline inference
docker run -e HF_TOKEN -e VLLM_WORKER_MULTIPROC_METHOD=spawn -v /root/.cache/huggingface:/root/.cache/huggingface --name gh200-test --gpus=all --entrypoint="" gh200-test bash -c '
python3 examples/offline_inference/basic/generate.py --model meta-llama/Llama-3.2-1B
python3 examples/basic/offline_inference/generate.py --model meta-llama/Llama-3.2-1B
'

2
.buildkite/scripts/hardware_ci/run-hpu-test.sh
View File

@@ -76,7 +76,7 @@ docker run --rm --runtime=habana --name="${container_name}" --network=host \
-e PT_HPU_LAZY_MODE=1 \
"${image_name}" \
/bin/bash -c '
cd vllm; timeout 120s python -u examples/offline_inference/basic/generate.py --model facebook/opt-125m
cd vllm; timeout 120s python -u examples/basic/offline_inference/generate.py --model facebook/opt-125m
'
EXITCODE=$?

18
.buildkite/scripts/hardware_ci/run-xpu-test.sh
View File

@@ -34,15 +34,15 @@ docker run \
set -e
echo $ZE_AFFINITY_MASK
pip install tblib==3.1.0
python3 examples/offline_inference/basic/generate.py --model facebook/opt-125m --block-size 64 --enforce-eager
python3 examples/offline_inference/basic/generate.py --model facebook/opt-125m --block-size 64 -O3 -cc.cudagraph_mode=NONE
python3 examples/offline_inference/basic/generate.py --model facebook/opt-125m --block-size 64 --enforce-eager -tp 2 --distributed-executor-backend ray
python3 examples/offline_inference/basic/generate.py --model facebook/opt-125m --block-size 64 --enforce-eager -tp 2 --distributed-executor-backend mp
python3 examples/offline_inference/basic/generate.py --model facebook/opt-125m --block-size 64 --enforce-eager --attention-backend=TRITON_ATTN
python3 examples/offline_inference/basic/generate.py --model facebook/opt-125m --block-size 64 --enforce-eager --quantization fp8
python3 examples/offline_inference/basic/generate.py --model superjob/Qwen3-4B-Instruct-2507-GPTQ-Int4 --block-size 64 --enforce-eager
python3 examples/offline_inference/basic/generate.py --model ibm-research/PowerMoE-3b --block-size 64 --enforce-eager -tp 2
python3 examples/offline_inference/basic/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 facebook/opt-125m --block-size 64 --enforce-eager
python3 examples/basic/offline_inference/generate.py --model facebook/opt-125m --block-size 64 -O3 -cc.cudagraph_mode=NONE
python3 examples/basic/offline_inference/generate.py --model facebook/opt-125m --block-size 64 --enforce-eager -tp 2 --distributed-executor-backend ray
python3 examples/basic/offline_inference/generate.py --model facebook/opt-125m --block-size 64 --enforce-eager -tp 2 --distributed-executor-backend mp
python3 examples/basic/offline_inference/generate.py --model facebook/opt-125m --block-size 64 --enforce-eager --attention-backend=TRITON_ATTN
python3 examples/basic/offline_inference/generate.py --model facebook/opt-125m --block-size 64 --enforce-eager --quantization fp8
python3 examples/basic/offline_inference/generate.py --model superjob/Qwen3-4B-Instruct-2507-GPTQ-Int4 --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
cd tests
pytest -v -s v1/core --ignore=v1/core/test_reset_prefix_cache_e2e.py --ignore=v1/core/test_scheduler_e2e.py
pytest -v -s v1/engine

30
.buildkite/test-amd.yaml
View File

@@ -529,12 +529,12 @@ steps:
commands:
- pip install tensorizer # for tensorizer test
# for basic
- python3 offline_inference/basic/chat.py
- python3 offline_inference/basic/generate.py --model facebook/opt-125m
- python3 offline_inference/basic/generate.py --model meta-llama/Llama-2-13b-chat-hf --cpu-offload-gb 10
- python3 offline_inference/basic/classify.py
- python3 offline_inference/basic/embed.py
- python3 offline_inference/basic/score.py
- python3 basic/offline_inference/chat.py
- python3 basic/offline_inference/generate.py --model facebook/opt-125m
- python3 basic/offline_inference/generate.py --model meta-llama/Llama-2-13b-chat-hf --cpu-offload-gb 10
- python3 basic/offline_inference/classify.py
- python3 basic/offline_inference/embed.py
- python3 basic/offline_inference/score.py
# for multi-modal models
- python3 offline_inference/audio_language.py --seed 0
- python3 offline_inference/vision_language.py --seed 0
@@ -1169,7 +1169,7 @@ steps:
- pytest -v -s tests/models/test_transformers.py
# - pytest -v -s tests/models/multimodal/processing/
- pytest -v -s tests/models/multimodal/test_mapping.py -k 'not (Gemma3 or Qwen2VL or Qwen2_5_VL)'
- python3 examples/offline_inference/basic/chat.py
- python3 examples/basic/offline_inference/chat.py
# - python3 examples/offline_inference/vision_language.py --model-type qwen2_5_vl
# Whisper needs spawn method to avoid deadlock
- VLLM_WORKER_MULTIPROC_METHOD=spawn python3 examples/offline_inference/audio_language.py --model-type whisper
@@ -2208,12 +2208,12 @@ steps:
commands:
- pip install tensorizer # for tensorizer test
# for basic
- python3 offline_inference/basic/chat.py
- python3 offline_inference/basic/generate.py --model facebook/opt-125m
- python3 offline_inference/basic/generate.py --model meta-llama/Llama-2-13b-chat-hf --cpu-offload-gb 10
- python3 offline_inference/basic/classify.py
- python3 offline_inference/basic/embed.py
- python3 offline_inference/basic/score.py
- python3 basic/offline_inference/chat.py
- python3 basic/offline_inference/generate.py --model facebook/opt-125m
- python3 basic/offline_inference/generate.py --model meta-llama/Llama-2-13b-chat-hf --cpu-offload-gb 10
- python3 basic/offline_inference/classify.py
- python3 basic/offline_inference/embed.py
- python3 basic/offline_inference/score.py
# for multi-modal models
- python3 offline_inference/audio_language.py --seed 0
- python3 offline_inference/vision_language.py --seed 0
@@ -2789,7 +2789,7 @@ steps:
- pytest -v -s tests/models/test_transformers.py
# - pytest -v -s tests/models/multimodal/processing/
- pytest -v -s tests/models/multimodal/test_mapping.py -k 'not (Gemma3 or Qwen2VL or Qwen2_5_VL)'
- python3 examples/offline_inference/basic/chat.py
- python3 examples/basic/offline_inference/chat.py
# - python3 examples/offline_inference/vision_language.py --model-type qwen2_5_vl
# Whisper needs spawn method to avoid deadlock
- VLLM_WORKER_MULTIPROC_METHOD=spawn python3 examples/offline_inference/audio_language.py --model-type whisper
@@ -2816,7 +2816,7 @@ steps:
- vllm/platforms/cuda.py
commands:
- rocm-smi
- python3 examples/offline_inference/basic/chat.py
- python3 examples/basic/offline_inference/chat.py
# Attention
# num_heads2 broken by https://github.com/flashinfer-ai/flashinfer/issues/1353
- pytest -v -s tests/kernels/attention/test_attention_selector.py

2
.buildkite/test_areas/kernels.yaml
View File

@@ -96,7 +96,7 @@ steps:
- vllm/platforms/cuda.py
commands:
- nvidia-smi
- python3 examples/offline_inference/basic/chat.py
- python3 examples/basic/offline_inference/chat.py
# Attention
# num_heads2 broken by https://github.com/flashinfer-ai/flashinfer/issues/1353
- pytest -v -s tests/kernels/attention/test_attention_selector.py

13
.buildkite/test_areas/misc.yaml
View File

@@ -67,12 +67,13 @@ steps:
- examples/
commands:
- pip install tensorizer # for tensorizer test
- python3 offline_inference/basic/chat.py # for basic
- python3 offline_inference/basic/generate.py --model facebook/opt-125m
- python3 offline_inference/basic/generate.py --model meta-llama/Llama-2-13b-chat-hf --cpu-offload-gb 10
- python3 offline_inference/basic/classify.py
- python3 offline_inference/basic/embed.py
- python3 offline_inference/basic/score.py
# for basic
- python3 basic/offline_inference/chat.py
- python3 basic/offline_inference/generate.py --model facebook/opt-125m
- python3 basic/offline_inference/generate.py --model meta-llama/Llama-2-13b-chat-hf --cpu-offload-gb 10
- python3 basic/offline_inference/classify.py
- python3 basic/offline_inference/embed.py
- python3 basic/offline_inference/score.py
# for multi-modal models
- python3 offline_inference/audio_language.py --seed 0
- python3 offline_inference/vision_language.py --seed 0

2
.buildkite/test_areas/models_basic.yaml
View File

@@ -65,7 +65,7 @@ steps:
- pytest -v -s tests/models/test_transformers.py
- pytest -v -s tests/models/multimodal/processing/
- pytest -v -s tests/models/multimodal/test_mapping.py
- python3 examples/offline_inference/basic/chat.py
- python3 examples/basic/offline_inference/chat.py
- python3 examples/offline_inference/vision_language.py --model-type qwen2_5_vl
# Whisper needs spawn method to avoid deadlock
- VLLM_WORKER_MULTIPROC_METHOD=spawn python3 examples/offline_inference/audio_language.py --model-type whisper