Skip to content

test(ci): correct the mm_router VRAM profile from 18.7 to the measured 7.6 GiB (OPS-8117) #12848

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
dmitry-tokarev-nv wants to merge 1 commit into from
Closed

test(ci): correct the mm_router VRAM profile from 18.7 to the measured 7.6 GiB (OPS-8117) #12848

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 5 additions & 1 deletion tests/mm_router/test_router_rust_mm_frontend_decode_e2e.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -63,7 +63,11 @@
pytest.mark.gpu_1,
pytest.mark.model(VLLM_MM_MODEL),
pytest.mark.requested_vllm_kv_cache_bytes(1_719_075_000),
pytest.mark.profiled_vram_gib(18.7),
# Measured solo peak, which is what profiled_vram_gib means. The KV cap
# above pins the footprint, so this matches test_vllm_mm_router_e2e.py --
# same model, same cap, same 7.6 GiB. The previous 18.7 exceeded the
# multi-process budget, which made every test in this file exclusive.
pytest.mark.profiled_vram_gib(7.6),
]


Expand Down
6 changes: 5 additions & 1 deletion tests/mm_router/test_router_rust_mm_router_e2e.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -61,7 +61,11 @@
pytest.mark.gpu_1,
pytest.mark.model(VLLM_MM_MODEL),
pytest.mark.requested_vllm_kv_cache_bytes(1_719_075_000),
pytest.mark.profiled_vram_gib(18.7),
# Measured solo peak, which is what profiled_vram_gib means. The KV cap
# above pins the footprint, so this matches test_vllm_mm_router_e2e.py --
# same model, same cap, same 7.6 GiB. The previous 18.7 exceeded the
# multi-process budget, which made every test in this file exclusive.
pytest.mark.profiled_vram_gib(7.6),
]


Expand Down
Loading