[Feature] Spec-Overlap supporting DP-ATTN; PD-Disaggregation; npugraph mode (#12443)

This commit is contained in:
Even Zhou
2025-11-15 21:51:07 +08:00
committed by GitHub
parent 0d41ddfbd0
commit 2aec8b6e1b
24 changed files with 657 additions and 366 deletions

View File

@@ -59,7 +59,7 @@ wget -O "${BISHENG_NAME}" "${BISHENG_URL}" && chmod a+x "${BISHENG_NAME}" && "./
### Install sgl-kernel-npu
SGL_KERNEL_NPU_TAG="20251106"
SGL_KERNEL_NPU_TAG="20251110"
git clone --depth 1 https://github.com/sgl-project/sgl-kernel-npu.git --branch ${SGL_KERNEL_NPU_TAG}
# pin wheel to 0.45.1 ref: https://github.com/pypa/wheel/issues/662
pip install wheel==0.45.1