aboutsummaryrefslogtreecommitdiff
path: root/tests/check_workspace_api.py
diff options
context:
space:
mode:
authorOnur Gündüz <ogunduz@gmail.com>2026-06-22 17:11:26 +0200
committerOnur Gündüz <ogunduz@gmail.com>2026-06-22 17:11:26 +0200
commit74fc389fb382cc79f67b67591569144b3fa393bd (patch)
treee5b4925f4096a463aa6566585f4cd22433380a29 /tests/check_workspace_api.py
parentebdf85d4d3c96fd7015192a44b94bb3bcad19735 (diff)
downloadffwd-74fc389fb382cc79f67b67591569144b3fa393bd.tar.gz
ffwd-74fc389fb382cc79f67b67591569144b3fa393bd.zip
cuda: prune attention experiments
Diffstat (limited to 'tests/check_workspace_api.py')
-rw-r--r--tests/check_workspace_api.py9
1 files changed, 5 insertions, 4 deletions
diff --git a/tests/check_workspace_api.py b/tests/check_workspace_api.py
index 40bac11..05f0e8c 100644
--- a/tests/check_workspace_api.py
+++ b/tests/check_workspace_api.py
@@ -6,11 +6,12 @@ the synthetic fixture. Given a MODEL_DIR it loads real weights from that
directory instead and exercises the workspace and batch APIs. Needs only
python3 and a model directory (with vocab.json), no reference stack.
-The model must be mean-pooled: the test checks that a whole-sequence span pools
-to the embedding, which holds for mean pooling (pplx-embed, BERT/BGE) but not
-for last-token pooling (Qwen3). Use a pplx-embed model.
+For mean-pooled models, the test additionally checks that a whole-sequence span
+pools to the embedding and that half-spans recombine by token-count weighting.
+For last-token/CLS models, those mean-span identities are skipped because the
+sentence embedding and contextual span APIs intentionally pool different rows.
- tests/check_workspace_api.py --model-dir DIR # DIR = a pplx-embed model
+ tests/check_workspace_api.py --model-dir DIR
"""
import argparse