Skip to content

[TRTLLM-12807][feat] Wrap CuteDSL MLA decode as FMHA lib #15333

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

Closed
yuxianq wants to merge 4 commits into from
Closed

[TRTLLM-12807][feat] Wrap CuteDSL MLA decode as FMHA lib #15333

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
1fa665b
[None][feat] add CuteDSL FP8/FP16 MLA decode attention backend
haow-nv Jun 8, 2026
e274758
[None][feat] CuteDSL MLA decode: fp8 scaling fix, BF16 support, per-l…
haow-nv Jun 12, 2026
214ebd6
[None][fix] CuteDSL MLA decode: v1 paged-KV layout + CUDA-graph-safe …
haow-nv Jun 16, 2026
b893d83
[TRTLLM-12807][feat] Wrap CuteDSL MLA decode as FMHA lib
yuxianq Jun 13, 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
10 changes: 10 additions & 0 deletions .pre-commit-config.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -299,6 +299,11 @@ common-files: &common_files |
tensorrt_llm/_torch/custom_ops/userbuffers_custom_ops.py |
tensorrt_llm/_torch/cute_dsl_kernels/__init__.py |
tensorrt_llm/_torch/cute_dsl_kernels/blackwell/__init__.py |
tensorrt_llm/_torch/cute_dsl_kernels/blackwell/attention/__init__.py |
tensorrt_llm/_torch/cute_dsl_kernels/blackwell/attention/mla/__init__.py |
tensorrt_llm/_torch/cute_dsl_kernels/blackwell/attention/mla/mla_decode_fp16.py |
tensorrt_llm/_torch/cute_dsl_kernels/blackwell/attention/mla/mla_decode_fp8.py |
tensorrt_llm/_torch/cute_dsl_kernels/blackwell/attention/mla/mla_helpers.py |
tensorrt_llm/_torch/cute_dsl_kernels/blackwell/custom_pipeline.py |
tensorrt_llm/_torch/cute_dsl_kernels/blackwell/dense_blockscaled_gemm_persistent.py |
tensorrt_llm/_torch/cute_dsl_kernels/blackwell/utils.py |
Expand Down Expand Up @@ -1674,6 +1679,11 @@ legacy-files: &legacy_files |
tensorrt_llm/_torch/custom_ops/userbuffers_custom_ops.py |
tensorrt_llm/_torch/cute_dsl_kernels/__init__.py |
tensorrt_llm/_torch/cute_dsl_kernels/blackwell/__init__.py |
tensorrt_llm/_torch/cute_dsl_kernels/blackwell/attention/__init__.py |
tensorrt_llm/_torch/cute_dsl_kernels/blackwell/attention/mla/__init__.py |
tensorrt_llm/_torch/cute_dsl_kernels/blackwell/attention/mla/mla_decode_fp16.py |
tensorrt_llm/_torch/cute_dsl_kernels/blackwell/attention/mla/mla_decode_fp8.py |
tensorrt_llm/_torch/cute_dsl_kernels/blackwell/attention/mla/mla_helpers.py |
tensorrt_llm/_torch/cute_dsl_kernels/blackwell/custom_pipeline.py |
tensorrt_llm/_torch/cute_dsl_kernels/blackwell/dense_blockscaled_gemm_persistent.py |
tensorrt_llm/_torch/cute_dsl_kernels/blackwell/utils.py |
Expand Down
5 changes: 5 additions & 0 deletions legacy-files.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -291,6 +291,11 @@ tensorrt_llm/_torch/custom_ops/trtllm_gen_custom_ops.py
tensorrt_llm/_torch/custom_ops/userbuffers_custom_ops.py
tensorrt_llm/_torch/cute_dsl_kernels/__init__.py
tensorrt_llm/_torch/cute_dsl_kernels/blackwell/__init__.py
tensorrt_llm/_torch/cute_dsl_kernels/blackwell/attention/__init__.py
tensorrt_llm/_torch/cute_dsl_kernels/blackwell/attention/mla/__init__.py
tensorrt_llm/_torch/cute_dsl_kernels/blackwell/attention/mla/mla_decode_fp16.py
tensorrt_llm/_torch/cute_dsl_kernels/blackwell/attention/mla/mla_decode_fp8.py
tensorrt_llm/_torch/cute_dsl_kernels/blackwell/attention/mla/mla_helpers.py
tensorrt_llm/_torch/cute_dsl_kernels/blackwell/custom_pipeline.py
tensorrt_llm/_torch/cute_dsl_kernels/blackwell/dense_blockscaled_gemm_persistent.py
tensorrt_llm/_torch/cute_dsl_kernels/blackwell/utils.py
Expand Down
5 changes: 5 additions & 0 deletions pyproject.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -349,6 +349,11 @@ exclude = [
"tensorrt_llm/_torch/custom_ops/userbuffers_custom_ops.py",
"tensorrt_llm/_torch/cute_dsl_kernels/__init__.py",
"tensorrt_llm/_torch/cute_dsl_kernels/blackwell/__init__.py",
"tensorrt_llm/_torch/cute_dsl_kernels/blackwell/attention/__init__.py",
"tensorrt_llm/_torch/cute_dsl_kernels/blackwell/attention/mla/__init__.py",
"tensorrt_llm/_torch/cute_dsl_kernels/blackwell/attention/mla/mla_decode_fp16.py",
"tensorrt_llm/_torch/cute_dsl_kernels/blackwell/attention/mla/mla_decode_fp8.py",
"tensorrt_llm/_torch/cute_dsl_kernels/blackwell/attention/mla/mla_helpers.py",
"tensorrt_llm/_torch/cute_dsl_kernels/blackwell/custom_pipeline.py",
"tensorrt_llm/_torch/cute_dsl_kernels/blackwell/dense_blockscaled_gemm_persistent.py",
"tensorrt_llm/_torch/cute_dsl_kernels/blackwell/utils.py",
Expand Down
5 changes: 5 additions & 0 deletions ruff-legacy.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -308,6 +308,11 @@ include = [
"tensorrt_llm/_torch/custom_ops/userbuffers_custom_ops.py",
"tensorrt_llm/_torch/cute_dsl_kernels/__init__.py",
"tensorrt_llm/_torch/cute_dsl_kernels/blackwell/__init__.py",
"tensorrt_llm/_torch/cute_dsl_kernels/blackwell/attention/__init__.py",
"tensorrt_llm/_torch/cute_dsl_kernels/blackwell/attention/mla/__init__.py",
"tensorrt_llm/_torch/cute_dsl_kernels/blackwell/attention/mla/mla_decode_fp16.py",
"tensorrt_llm/_torch/cute_dsl_kernels/blackwell/attention/mla/mla_decode_fp8.py",
"tensorrt_llm/_torch/cute_dsl_kernels/blackwell/attention/mla/mla_helpers.py",
"tensorrt_llm/_torch/cute_dsl_kernels/blackwell/custom_pipeline.py",
"tensorrt_llm/_torch/cute_dsl_kernels/blackwell/dense_blockscaled_gemm_persistent.py",
"tensorrt_llm/_torch/cute_dsl_kernels/blackwell/utils.py",
Expand Down
2 changes: 2 additions & 0 deletions tensorrt_llm/_torch/attention_backend/fmha/__init__.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -13,6 +13,7 @@
# See the License for the specific language governing permissions and
# limitations under the License.

from .cute_dsl import CuteDslMlaFmha
from .fallback import FallbackFmha
from .flashinfer_trtllm_gen import FlashInferTrtllmGenFmha
from .interface import Fmha
Expand All @@ -22,6 +23,7 @@
__all__ = [
"DEFAULT_FMHA_LIBS",
"FMHA_LIBS",
"CuteDslMlaFmha",
"FallbackFmha",
"FlashInferTrtllmGenFmha",
"Fmha",
Expand Down
Loading
Loading