thqq479

> I met the same problem. This issue is usually caused by insufficient GPU memory. Try to reserve more GPU memory for DeepEP buffer how to set this？

In this version, the H100 machine does not have RDMA. Is it feasible to use NVLINK for transmission between nodes within a single machine? @alogfans

The same issue, have you solved it yet? @ChuanhongLi

On the H100 machine, I tried the latest tent version, but I still got the same OOM error @alogfans @ShangmingCai Hi,Could you please assist us?

When SGLANG_MOONCAKE_CUSTOM_MEM_POOL is set to true, the GPU memory becomes abnormal/ malfunctioning

> > On the H100 machine, I tried the latest tent version, but I still got the same OOM error [@alogfans](https://github.com/alogfans) [@ShangmingCai](https://github.com/ShangmingCai) Hi,Could you please assist us? > > [@thqq479](https://github.com/thqq479)...

> Enable `USE_CUDA` and `USE_MNNVL` in https://github.com/kvcache-ai/Mooncake/blob/897728ddbfb8c1269c3cb64b4097e281d203faff/mooncake-common/common.cmake Then compile and install from source. > > Set this up with sglang: > > ``` > export SGLANG_MOONCAKE_CUSTOM_MEM_POOL=True > export MC_FORCE_MNNVL=True >...

> [@thqq479](https://github.com/thqq479) It requires CUDA 12.8+. What is your CUDA version? nvcc --version nvcc: NVIDIA (R) Cuda compiler driver Copyright (c) 2005-2025 NVIDIA Corporation Built on Wed_Jan_15_19:20:09_PST_2025 Cuda compilation tools,...

@alogfans @ShangmingCai Hi, may I ask how I should proceed to further investigate this issue, or what environment you tested in?

> > [@alogfans](https://github.com/alogfans) [@ShangmingCai](https://github.com/ShangmingCai) Hi, may I ask how I should proceed to further investigate this issue, or what environment you tested in? > > GB200 The GB200 model is...