Skip to content

Unify and modularize decode and prefill test. #1375

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

Merged
merged 8 commits into from
Aug 13, 2025
Merged

Unify and modularize decode and prefill test. #1375

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
8 commits
Select commit Hold shift + click to select a range
3e8e9bd
Unify and modularize decode and prefill test.
weireweire Aug 4, 2025
261782c
update test list. rename file
weireweire Aug 5, 2025
9f8d1ff
fix trtllm-gen break by a check
weireweire Aug 12, 2025
93699aa
remove not needed plan check for trtllm-gen
weireweire Aug 12, 2025
05cc0c5
Merge branch 'main' of github.com:flashinfer-ai/flashinfer into trtll…
yyihuang Aug 13, 2025
4a3a857
fix conflicts
yyihuang Aug 13, 2025
49b6888
Merge branch 'main' of github.com:flashinfer-ai/flashinfer into trtll…
yyihuang Aug 13, 2025
b6d27c3
fix conflicts
yyihuang Aug 13, 2025
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
7 changes: 7 additions & 0 deletions flashinfer/decode.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1288,6 +1288,13 @@ def run(

self._cached_module.paged_run(*run_args)
else:
# trtllm-gen does not need plan info
if self._backend == "trtllm-gen" and self._plan_info is None:
plan_info: List[int] = []
else:
plan_info = self._plan_info
assert plan_info is not None, "plan info is not initialized"

run_args = [
self._float_workspace_buffer,
self._int_workspace_buffer,
Expand Down
4 changes: 2 additions & 2 deletions scripts/run_test_blackwell_attention_kernels.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -7,8 +7,8 @@ pytest -s tests/test_blackwell_fmha.py
pytest -s tests/test_deepseek_mla.py

# trtllm-gen
pytest -s tests/test_trtllm_gen_context.py
pytest -s tests/test_trtllm_gen_decode.py
pytest -s tests/test_trtllm_gen_attention.py
pytest -s tests/test_trtllm_gen_mla.py

# cudnn
pytest -s tests/test_cudnn_decode.py
Expand Down
Loading