diff options
| author | Onur Gündüz <ogunduz@gmail.com> | 2026-06-22 17:11:26 +0200 |
|---|---|---|
| committer | Onur Gündüz <ogunduz@gmail.com> | 2026-06-22 17:11:26 +0200 |
| commit | 74fc389fb382cc79f67b67591569144b3fa393bd (patch) | |
| tree | e5b4925f4096a463aa6566585f4cd22433380a29 /tests/check_workspace_api.py | |
| parent | ebdf85d4d3c96fd7015192a44b94bb3bcad19735 (diff) | |
| download | ffwd-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.py | 9 |
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 |
