xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2026-01-03 23:53:10 +08:00
Code Issues Packages Projects Releases Wiki Activity

[Bugfix] Fix eagle dp tests on A100 (#31241)

Browse Source 
Signed-off-by: Richard Zou <zou3519@gmail.com>
This commit is contained in:
Richard Zou 2025-12-24 19:05:04 -05:00 committed by GitHub
parent bc5ef333e0
commit 254f6b9867
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 7 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
tests/v1/distributed/test_eagle_dp.py
View File

@ -16,7 +16,12 @@ DP_SIZE = int(os.getenv("DP_SIZE", 2))
@pytest.mark.asyncio
async def test_run_eagle_dp():
async def test_run_eagle_dp(monkeypatch: pytest.MonkeyPatch):
# This test checks that running a model with and without eagle
# leads to identical tokens. This is only true in batch invariant mode
# (because the target model verifies all draft tokens in one big forward pass)
monkeypatch.setenv("VLLM_BATCH_INVARIANT", "1")
target_model = "meta-llama/Llama-3.1-8B-Instruct"
draft_model = "yuhuili/EAGLE-LLaMA3.1-Instruct-8B"
@ -29,6 +34,7 @@ async def test_run_eagle_dp():
data_parallel_backend="mp", # ray takes more time
trust_remote_code=True,
max_model_len=16384,
attention_config={"backend": "FLASH_ATTN"},
)
eagle_engine_args = replace(