Qinghua Zhou 359e681e8e ep(bench): mscclpp_ep_bench uses NCCL-EP-style random top-k routing (#832) ...

## Summary
Replaces the deterministic `(t*K+j) % E` expert assignment in
`mscclpp_ep_bench.cu`
with the same randomized top-k routing scheme used by the NCCL-EP
benchmark, so the
C++ LL benchmark exercises a realistic, non-uniform expert distribution.

## Changes
- Per-token scores drawn from `|N(0,1)| + 1` with a rank-seeded
`std::mt19937(1+rank)`.
- `std::partial_sort` selects the top-K experts per token (descending).
- Randomly masks 10 (token, slot) positions to `-1` to exercise the LL
kernels'
  invalid-index handling (guarded at `low_latency.cu:278` and `:726`).
- Byte accounting now counts only valid (`>= 0`) selections.
- Added `<random>` / `<utility>` includes; clang-format-14 clean.

---------

Co-authored-by: Binyang Li <binyli@microsoft.com>
Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com>

2026-07-13 14:32:56 -07:00

..

ep

ep(bench): mscclpp_ep_bench uses NCCL-EP-style random top-k routing (#832)

2026-07-13 14:32:56 -07:00