Skip to content

[PyTorch] Support FA3 MLA CP feature #1907

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

Open
wants to merge 2 commits into
base: main
Choose a base branch
from
+205 −104
Open

[PyTorch] Support FA3 MLA CP feature #1907

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
3a6b27d
feature(FA3,MLA,CP):
zhujian19891203 Jun 28, 2025
2f3c72d
Merge branch 'main' into fa3_mla_cp
zhujian19891203 Jun 28, 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
2 changes: 1 addition & 1 deletion docs/examples/attention/attention.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -390,7 +390,7 @@
"| Attention Backend | Precision | Architecture | Sliding Window Attention | MQA/GQA | Multi-Latent Attention | Context Parallelism | Determinism Possible |\n",
"| :---------------- | :-------- | :----------- | :----------------------- | :------ | :--------------------- | :------------------ | :------------ |\n",
"| cuDNN attention (all frameworks) | BF16, FP16, FP8 (PyTorch only) | sm80+ | No | Yes | Yes | Yes (`bshd`,`sbhd`, `thd`) | Yes |\n",
"| flash-attention (PyTorch) | BF16, FP16 | sm80+ | Yes | Yes | No | Yes (`bshd`,`thd`) | Yes |\n",
"| flash-attention (PyTorch) | BF16, FP16 | sm80+ | Yes | Yes | Yes | Yes (`bshd`,`thd`) | Yes |\n",
"| Framework-native attention | BF16, FP16, FP32 | Any | No, unless used as a mask | Yes | Yes (PyTorch only) | No | Yes |\n",
"\n",
"Some unit tests are provided to serve as a starting point for integrating such features into users' models. For example,\n",
Expand Down
12 changes: 12 additions & 0 deletions tests/pytorch/fused_attn/test_fused_attn_with_cp.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -32,6 +32,18 @@
"cp_2_3": ModelConfig(
2, 12, 2, 128, 4096, 4096, 0.0, "no_mask", "no_bias", window_size=(512, 512)
), # GQA
"cp_3_0": ModelConfig(
2, 12, 12, 128, 4096, 4096, 0.0, "causal", "no_bias", head_dim_v=64
), # MLA
"cp_3_1": ModelConfig(
2, 12, 12, 128, 4096, 4096, 0.0, "no_mask", "no_bias", head_dim_v=64
), # MLA
"cp_3_2": ModelConfig(
2, 12, 12, 128, 4096, 4096, 0.0, "causal", "no_bias", window_size=(512, 0), head_dim_v=64
), # MLA
"cp_3_3": ModelConfig(
2, 12, 12, 128, 4096, 4096, 0.0, "no_mask", "no_bias", window_size=(512, 512), head_dim_v=64
), # MLA
}


Expand Down
Loading