biondizzle/nvfp4-megamoe-kernel
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
2,195 Commits 1 Branch 17 Tags
107d62dd76215946fcdda9240f72b6c0c1dbb708
Commit Graph

2 Commits

Author SHA1 Message Date
biondizzle
617da29a5b fix: assert topk_idx is not None in CSA layers — no silent fallback to SWA-only 
The indexer silently returning None caused CSA layers to attend over only the
SWA window (128 tokens), not the compressed sparse KV. This went undetected
because the model still produced plausible output at short context. The assert
makes any future indexer regression immediately visible.
 2026-06-02 06:14:23 +00:00
biondizzle
938e9079ce probe: indexer and compressor weight shapes from checkpoint 2026-06-02 04:36:35 +00:00