Menu

Individual skill

build-triton-ascend-binned-moe-routing

Build capacity-limited binned MoE gather, scatter, and router-weight-gradient kernels for Triton-Ascend using sorted expert bins, UB sub-block buffering, and vector-core-aware tiling. Use when an agent ports MegaBlocks binned routing, packs tokens into fixed expert-capacity tensors, restores top-k token outputs, or must handle sub-blocks that cross expert boundaries.

skills/build-triton-ascend-binned-moe-routing/SKILL.md

Read pinned source

Source commit 4ab5ee7adf47755ecd42723f55f4c58e38be95a7

What was checked

Matches the observed repository HEAD
Yes
Scanner rules are current
Yes
Repository scan complete
No
Skill scan complete
Yes
Observed behavior
Instructions only
Last checked
Nov 4, 2026

These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.

Install this skill

Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.

An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.

Repository context

Repository stars (not skill ratings)
189
Repository last updated
Aug 15, 2026
License
Apache-2.0

Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.

Files and excerpt

File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.

Browse files
Read excerpt

# Build Triton-Ascend Binned MoE Routing

## Goal

Map sorted token assignments into a tensor shaped experts by expert_capacity by hidden_size, truncate overflow per expert, and implement the inverse scatter and router-weight gradient.

## Workflow

1. Require bin_ids to be nondecreasing expert IDs aligned with indices.
2. Interpret bins[e] as the inclusive cumulative assignment count through expert e.
3. For gather, compute each assignment's offset within its expert and keep only offsets below expert_capacity.
4. Buffer rows for the current expert in UB; flush them when the expert ID changes inside a sub-block.
5. For scatter, load valid expert-capacity rows, store to unique assignment slots, optionally scale, and reduce TOP_K slots per token.
6. For wgrad, dot each kept expert row with the gradient of indices[i] // TOP_K.