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

Mirroring the test definitions (2025-10-22) (#27362)

Browse Source 
Signed-off-by: Alexei V. Ivanov <alexei.ivanov@amd.com>
This commit is contained in:
Alexei-V-Ivanov-AMD
2025-10-23 11:02:26 -05:00
committed by GitHub
parent 3fa2c12185
commit 295c7f0267
1 changed files with 9 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

11
.buildkite/test-amd.yaml
View File

@ -395,7 +395,9 @@ steps:
- python3 offline_inference/basic/embed.py
- python3 offline_inference/basic/score.py
- python3 offline_inference/spec_decode.py --test --method eagle --num_spec_tokens 3 --dataset-name hf --dataset-path philschmid/mt-bench --num-prompts 80 --temp 0 --top-p 1.0 --top-k -1 --tp 1 --enable-chunked-prefill --max-model-len 2048
- python3 offline_inference/spec_decode.py --test --method eagle3 --num_spec_tokens 3 --dataset-name hf --dataset-path philschmid/mt-bench --num-prompts 80 --temp 0 --top-p 1.0 --top-k -1 --tp 1 --enable-chunked-prefill --max-model-len 2048
# https://github.com/vllm-project/vllm/pull/26682 uses slightly more memory in PyTorch 2.9+ causing this test to OOM in 1xL4 GPU
- python3 offline_inference/spec_decode.py --test --method eagle3 --num_spec_tokens 3 --dataset-name hf --dataset-path philschmid/mt-bench --num-prompts 80 --temp 0 --top-p 1.0 --top-k -1 --tp 1 --enable-chunked-prefill --max-model-len 1536
#- python3 offline_inference/spec_decode.py --test --method eagle3 --num_spec_tokens 3 --dataset-name hf --dataset-path philschmid/mt-bench --num-prompts 80 --temp 0 --top-p 1.0 --top-k -1 --tp 1 --enable-chunked-prefill --max-model-len 2048
- label: Platform Tests (CUDA) # 4min
timeout_in_minutes: 15
@ -436,7 +438,11 @@ steps:
--num-shards=$$BUILDKITE_PARALLEL_JOB_COUNT \
--ignore=lora/test_chatglm3_tp.py \
--ignore=lora/test_llama_tp.py \
--ignore=lora/test_llm_with_multi_loras.py
--ignore=lora/test_llm_with_multi_loras.py \
--ignore=lora/test_olmoe_tp.py \
--ignore=lora/test_deepseekv2_tp.py \
--ignore=lora/test_gptoss.py \
--ignore=lora/test_qwen3moe_tp.py
parallelism: 4
- label: PyTorch Compilation Unit Tests # 15min
@ -1208,6 +1214,7 @@ steps:
- pytest -v -s -x lora/test_chatglm3_tp.py
- pytest -v -s -x lora/test_llama_tp.py
- pytest -v -s -x lora/test_llm_with_multi_loras.py
- pytest -v -s -x lora/test_olmoe_tp.py
- label: Weight Loading Multiple GPU Test # 33min
timeout_in_minutes: 45