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

[compile] Fix extra cache save on warm start. (#35921)

Browse Source 
Signed-off-by: zhxchen17 <zhxchen17@fb.com>
This commit is contained in:
Zhengxu Chen
2026-03-04 23:56:30 -05:00
committed by GitHub
parent 26366009c5
commit dd6dbd93f8
2 changed files with 27 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
tests/compile/test_startup.py
View File

@@ -61,11 +61,11 @@ def test_moe_startup(monkeypatch, vllm_runner, fresh_vllm_cache):
counters.clear()
with compilation_counter.expect(
num_compiled_artifacts_loaded=3,
# TODO: warm start should not save any artifacts
# https://github.com/vllm-project/vllm/issues/35708
num_compiled_artifacts_saved=1,
num_compiled_artifacts_saved=0,
):
_run_vllm(vllm_runner)
assert counters["aot_autograd"]["total"] == 30
assert counters["aot_autograd"]["autograd_cache_miss"] == 0
assert counters["aot_autograd"]["autograd_cache_hit"] == 1
assert (
counters["aot_autograd"]["autograd_cache_hit"] == 0
) # No miss at aot_autograd level causing disk I/O.