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

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