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

[CI] Replace large models with tiny alternatives in tests (#24057)

Browse Source 
Signed-off-by: Tahsin Tunan <tahsintunan@gmail.com>
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Nick Hill <nhill@redhat.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
This commit is contained in:
Tahsin Tunan
2025-10-16 20:51:27 +06:00
committed by GitHub
parent 02d709a6f1
commit 43721bc67f
17 changed files with 118 additions and 59 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
tests/basic_correctness/test_cumem.py
View File

@@ -120,7 +120,7 @@ def test_cumem_with_cudagraph():
"model",
[
# sleep mode with safetensors
"meta-llama/Llama-3.2-1B",
"hmellor/tiny-random-LlamaForCausalLM",
# sleep mode with pytorch checkpoint
"facebook/opt-125m",
],
@@ -174,7 +174,7 @@ def test_end_to_end(model: str):
@create_new_process_for_each_test()
def test_deep_sleep():
model = "Qwen/Qwen3-0.6B"
model = "hmellor/tiny-random-LlamaForCausalLM"
free, total = torch.cuda.mem_get_info()
used_bytes_baseline = total - free # in case other process is running
llm = LLM(model, enable_sleep_mode=True)