Spaces:
Running on Zero
Running on Zero
Commit ·
cd5cb58
1
Parent(s): 669c9d8
Pin compatible CUTLASS DSL
Browse files- requirements.txt +2 -1
requirements.txt
CHANGED
|
@@ -22,7 +22,8 @@ comfy-kitchen==0.2.26
|
|
| 22 |
# NVIDIA Sol-Engine's released sparse-attention package, pinned to the H3 release. The native SM120 path uses
|
| 23 |
# CuTe DSL; the package retains its portable Triton fallback if that optional backend cannot initialize.
|
| 24 |
sol-attn @ git+https://github.com/NVlabs/Sana.git@46031940ba8af5d18054217e571149579424c0b1#subdirectory=techniques/sparse_backends
|
| 25 |
-
|
|
|
|
| 26 |
cuda-python>=13.0
|
| 27 |
# Sol-Attn compiles its CuTe callable with `--enable-tvm-ffi`, but its package currently leaves this transitive
|
| 28 |
# runtime undeclared. Without it the SM120 path compiles up to dispatch and then falls back to dense attention.
|
|
|
|
| 22 |
# NVIDIA Sol-Engine's released sparse-attention package, pinned to the H3 release. The native SM120 path uses
|
| 23 |
# CuTe DSL; the package retains its portable Triton fallback if that optional backend cannot initialize.
|
| 24 |
sol-attn @ git+https://github.com/NVlabs/Sana.git@46031940ba8af5d18054217e571149579424c0b1#subdirectory=techniques/sparse_backends
|
| 25 |
+
# Sol-Engine's Aug-03 H3 kernel targets the 4.5 `cute.math.fmax` signature; 4.6 changed that API.
|
| 26 |
+
nvidia-cutlass-dsl==4.5.3
|
| 27 |
cuda-python>=13.0
|
| 28 |
# Sol-Attn compiles its CuTe callable with `--enable-tvm-ffi`, but its package currently leaves this transitive
|
| 29 |
# runtime undeclared. Without it the SM120 path compiles up to dispatch and then falls back to dense attention.
|