Skip to content
Merged
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
9 changes: 9 additions & 0 deletions tests/test-llama-archs.cpp
Original file line number Diff line number Diff line change
Expand Up @@ -366,6 +366,15 @@ static gguf_context_ptr get_gguf_ctx(const llm_arch arch, const bool moe) {
arch == LLM_ARCH_KOLIBRI1) {
n_head_kv = 2; // GQA coverage
}
if (arch == LLM_ARCH_BLACKMAMBA) {
// engine#2444: blackmamba takes its Switch-MoE branch whenever n_ff(i) != 0 (blackmamba.cpp:58), and that branch
// sizes ffn_gate_inp/ffn_* from n_ff_exp -- so a fixture written with the generic non-zero n_ff and no expert
// width aborts in the loader (t_meta.ne[dim] >= 1). The generic hparams are not enough for this arch.
ms.add_kv(LLM_KV_EXPERT_COUNT, uint32_t(2));
ms.add_kv(LLM_KV_EXPERT_USED_COUNT, uint32_t(2));
ms.add_kv(LLM_KV_EXPERT_FEED_FORWARD_LENGTH, n_ff);
}

if (arch == LLM_ARCH_BEAM) {
n_head = 4;
n_head_kv = 2;
Expand Down