Skip to content

GitLab

Unverified Commit 295c7f02 authored by Alexei-V-Ivanov-AMD's avatar Alexei-V-Ivanov-AMD Committed by GitHub
Browse files

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


Signed-off-by: default avatarAlexei V. Ivanov <alexei.ivanov@amd.com>
parent 3fa2c121
Show whitespace changes
Inline Side-by-side
Showing with 9 additions and 2 deletions
.buildkite/test-amd.yaml
View file @ 295c7f02
......@@ -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
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment