- Keep only Qwen3.5, Qwen3.5-MTP and Qwen4Exp model paths; trim the model registry to 41 entries - Delete idle attention backends (MLA, FlashInfer, ROCm-only, quant backends) and dead GDN CuTeDSL kernels - Remove inc/quark quant loaders; keep compressed-tensors and Marlin - Drop the Rust frontend, pooling entrypoints, and idle test suites - Rebuild kernels for sm_80;sm_86 and strip the extensions - Verified: full import sweep clean (optional deps only) and a dummy-load Qwen3.5 engine run on RTX 3090 via the Triton GDN path Co-authored-by: Hinata <hinata@idihore.id> Signed-off-by: MOVZX <movzx@yahoo.com>
13 lines
275 B
Plaintext
13 lines
275 B
Plaintext
# Should be mirrored in pyproject.toml
|
|
cmake>=3.26.1
|
|
ninja
|
|
packaging>=24.2
|
|
setuptools>=78.1.1,<81.0.0
|
|
setuptools-scm>=8
|
|
torch==2.14.0
|
|
wheel
|
|
jinja2>=3.1.6
|
|
regex
|
|
build
|
|
protobuf >= 5.29.6, !=6.30.*, !=6.31.*, !=6.32.*, !=6.33.0.*, !=6.33.1.*, !=6.33.2.*, !=6.33.3.*, !=6.33.4.*
|