scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-09-21 00:21:49 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 74

test: source the gemma context window limits and isolate the cost map cache

Browse source
This commit is contained in:
mateo-berri 2026-09-18 15:43:07 -07:00
parent 55249c7128
commit 44034c1d5e
1 changed files with 3 additions and 4 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

7
tests/test_litellm/llms/vertex_ai/vertex_ai_partner_models/gemma/test_vertex_ai_gemma_global_endpoint.py
View file

@ -180,12 +180,11 @@ class TestCreateVertexURLGemma:
# ---------------------------------------------------------------------------
def test_gemma_maas_context_window_matches_google(monkeypatch):
monkeypatch.setenv("LITELLM_LOCAL_MODEL_COST_MAP", "True")
monkeypatch.setattr(litellm, "model_cost", litellm.get_model_cost_map(url=""))
def test_gemma_maas_context_window_matches_google(local_model_cost_map):
info = litellm.get_model_info("vertex_ai/google/gemma-4-26b-a4b-it-maas")
# 262,144 context length and 128,000 maximum output per Google's model page, checked 2026-09-18:
# https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/maas/google/gemma-4-26b-a4b-it
assert info["max_input_tokens"] == 262144
assert info["max_output_tokens"] == 128000