feat(ops): argMax(dim) DSL op with StableHLO lowering + CPU kernel#800

Merged

michalharakal merged 3 commits into

functiongemma-selfcompile

Jul 8, 2026

Commits on Jul 8, 2026

feat(ops): add argMax(dim) tensor op with StableHLO lowering + CPU kernel

michalharakal
and
claude
committed
chore(api): sync .api dumps for argMax (fixes apiCheck)

michalharakal
and
claude
committed
fix(ops): argMax eager result must be a portable float tensor (native/wasm)

michalharakal
and
claude
committed