|
GPU ↔ FPGA over PCIe: asynchronous P2P / GPUDirect RDMA
|
|
0
|
45
|
September 24, 2026
|
|
GLM-4.7-FP8 on 4× DGX Spark via SGLang: 2.5× speedup (8.2 → 25 tok/s) just by enabling RDMA
|
|
0
|
255
|
June 18, 2026
|
|
ConnectX-7 RoCEv2 RC QP out-of-order receive behavior with non-NVIDIA packet-spraying switches
|
|
2
|
405
|
June 15, 2026
|
|
Reducing Memory Registration Overhead in DOCA RDMA Applications
|
|
1
|
112
|
June 10, 2026
|
|
[Inception Member] RustFS (26k+ Stars) Seeking Guidance on Rust SDK for DOCA & EC/RDMA Offloading
|
|
3
|
340
|
June 2, 2026
|
|
DOCA RDMA CM: Can multiple RDMA contexts listen on the same device/port in one process?
|
|
1
|
88
|
June 1, 2026
|
|
Dual DGX Spark: NCCL capped at 2.80 GB/s + ib_write_bw crashes at 128KB syndrom 0x88 — matches thread 366266 with additional RoCE degradation
|
|
1
|
420
|
April 20, 2026
|
|
NCCL bandwidth capped at 3 GB/s, GPU PCIe topology reports Gen1 x1 on DGX Spark FE
|
|
5
|
739
|
April 14, 2026
|
|
Does CX6-LX support RTTCC?
|
|
2
|
100
|
April 2, 2026
|
|
Doca_mmap_create_from_export segfaults when local mmaps are created before doca_rdma_create
|
|
0
|
51
|
March 24, 2026
|
|
Unable to reproduce cuObject example
|
|
1
|
161
|
February 25, 2026
|
|
GPUDirect RDMA in CC mode
|
|
0
|
139
|
February 5, 2026
|
|
How to Connect a ConnectX Adapter Using an NVMe PCIe 5.0 x4 via 3 MCIO Connector
|
|
1
|
202
|
January 26, 2026
|
|
How can I enable P2P from a PCIe video accelerator to an NVIDIA L4 GPU when dma‑buf import into CUDA fails but GPU→accelerator P2P works?
|
|
0
|
142
|
January 7, 2026
|
|
RDMA on jetson AGX orin
|
|
2
|
228
|
December 12, 2025
|