Expand description
2026-09-25: The Kimi K3 tensor-parallel plan (metrale_model_weights::kimi_k3_host::tp::tensor_plan) in TpShardKind terms.
Head counts on config are per rank; the returned sizes are full, local
heads times tp_world_size.
Owner: model-arch, Kimi K3. Invariants: none beyond the types.
Functionsยง
- supports_
tp - 2026-09-25: Always true: the Kimi K3 loader binds tensor-parallel shards.
- tensor_
plan - 2026-09-25:
(kind, full_out, full_in)for one checkpoint key. A key the plan does not name isReplicated.