- 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>
23 lines
512 B
Plaintext
23 lines
512 B
Plaintext
# Common dependencies
|
|
-r common.txt
|
|
--extra-index-url=https://wheels.vllm.ai/xpu/
|
|
triton==3.8.0+xpu
|
|
|
|
ray>=2.9
|
|
cmake>=3.26.1
|
|
packaging>=24.2
|
|
setuptools-scm>=8
|
|
setuptools>=78.1.1,<81.0.0
|
|
wheel
|
|
jinja2>=3.1.6
|
|
datasets # for benchmark scripts
|
|
numba == 0.65.0 # Required for N-gram speculative decoding
|
|
--extra-index-url=https://download.pytorch.org/whl/xpu
|
|
torch==2.14.0
|
|
torchaudio
|
|
torchvision
|
|
torchcodec >= 0.14 # Required for the torchcodec video decoding backend
|
|
|
|
auto_round_lib==0.16.0
|
|
vllm_xpu_kernels==0.1.15.4
|