Shangyan Zhou 9eb2f84b3e Optimize intranode combine. (#247) ...

* Increase the test round.

* Add warp synchronization.

* Shuffle the send warps.

* Add time elapsed into bench result.

2025-06-24 09:10:23 +08:00

..

test_internode.py

Use one qp per sm for internode normal kernels (#181)

2025-06-13 14:37:59 +08:00

test_intranode.py

Optimize intranode combine. (#247)

2025-06-24 09:10:23 +08:00

test_low_latency.py

Remove the low-latency usage flag (#214)

2025-06-16 13:30:14 +08:00

utils.py

Optimize intranode combine. (#247)

2025-06-24 09:10:23 +08:00