Skip to content

apriel2 modeling bug #450

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
tscholak merged 5 commits into from
Jan 19, 2026
Merged

apriel2 modeling bug #450

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
e8b93e0
apriel2 modeling bug
oleksost Jan 16, 2026
303206b
kda fix
oleksost Jan 16, 2026
b6449db
chunked prefil mode recurrent state
oleksost Jan 19, 2026
c3a6b44
Fix GDN/KDA bugs, require CUDA kernels, add cache-aware tests (#451)
tscholak Jan 19, 2026
f6f133b
Merge branch 'main' into oo/apriel_modeling_bug
tscholak Jan 19, 2026
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
406 changes: 0 additions & 406 deletions fast_llm_external_models/apriel2/cache.py
View file
Open in desktop

This file was deleted.

838 changes: 512 additions & 326 deletions fast_llm_external_models/apriel2/modeling_apriel2.py
View file
Open in desktop

Large diffs are not rendered by default.

4 changes: 2 additions & 2 deletions fast_llm_external_models/tests/test_apriel2/conftest.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -7,7 +7,7 @@
import torch
from transformers import LlavaConfig, LlavaForConditionalGeneration, MistralConfig

from fast_llm_external_models.apriel2.cache import _AttentionCache, _SSMCache
from fast_llm_external_models.apriel2.modeling_apriel2 import _AttentionCache, _SSMCache


# Register custom marks
Expand Down Expand Up @@ -831,7 +831,7 @@ def apriel2_config_with_bias():
@pytest.fixture
def apriel2_cache(apriel2_config_tiny):
"""Create empty Apriel2Cache from tiny config."""
from fast_llm_external_models.apriel2.cache import Apriel2Cache
from fast_llm_external_models.apriel2.modeling_apriel2 import Apriel2Cache

return Apriel2Cache(apriel2_config_tiny)

Expand Down
2 changes: 1 addition & 1 deletion fast_llm_external_models/tests/test_apriel2/test_cache_apriel2_specific.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -18,7 +18,7 @@
import pytest
import torch

from fast_llm_external_models.apriel2.cache import Apriel2Cache
from fast_llm_external_models.apriel2.modeling_apriel2 import Apriel2Cache

# =============================================================================
# STOCHASTIC MIXER ROUTING
Expand Down
2 changes: 1 addition & 1 deletion fast_llm_external_models/tests/test_apriel2/test_cache_contracts.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -27,7 +27,7 @@
import pytest
import torch

from fast_llm_external_models.apriel2.cache import Apriel2Cache, _AttentionCache
from fast_llm_external_models.apriel2.modeling_apriel2 import Apriel2Cache, _AttentionCache

# =============================================================================
# SECTION 1: FULL ATTENTION - _AttentionCache vs DynamicLayer
Expand Down
Loading
Loading