GitLab

Signed-off-by: LucasWilkinson <lwilkinson@neuralmagic.com>

Signed-off-by: omahs <73983677+omahs@users.noreply.github.com>

Implements dual-chunk-flash-attn backend for dual chunk attention with sparse attention support (#11844)

Signed-off-by: kaixih <kaixih@nvidia.com>

Signed-off-by: DefTruth <qiustudent_r@163.com>

Signed-off-by: DefTruth <qiustudent_r@163.com>

优化bf16精度
解决bf16精度问题，解决cudagraph精度问题

Signed-off-by: Gregory Shtrasberg <Gregory.Shtrasberg@amd.com>
Co-authored-by: Micah Williamson <micah.williamson@amd.com>

Signed-off-by: Lu Fang <lufang@fb.com>

2.修复medusa推理时内存访问越界问题
3.benchmark_moe添加deepseek_v2模型

Signed-off-by: Gregory Shtrasberg <Gregory.Shtrasberg@amd.com>

Signed-off-by: Max de Bayser <mbayser@br.ibm.com>
Signed-off-by: Flavia Beo <flavia.beo@ibm.com>
Co-authored-by: Flavia Beo <flavia.beo@ibm.com>

Signed-off-by: maleksan85 <maleksan@amd.com>
Co-authored-by: Aleksandr Malyshev <maleksan@amd.com>

2.examples中添加medusa readme
3.修复model_runner中input_positions配置错误的笔误，解决多个模型运行失败问题