From 39012bbcb1cae3f2a6f9a4f04d1de3859a0276ea Mon Sep 17 00:00:00 2001 From: GrEarl Date: Tue, 28 Jul 2026 04:39:02 +0900 Subject: [PATCH] llama : bump LLAMA_MAX_EXPERTS to 1024 for Kimi-K3 (896 experts) --- src/llama-hparams.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/src/llama-hparams.h b/src/llama-hparams.h index 727df6ca21e2..e1194334b756 100644 --- a/src/llama-hparams.h +++ b/src/llama-hparams.h @@ -7,7 +7,7 @@ // bump if necessary #define LLAMA_MAX_LAYERS 512 -#define LLAMA_MAX_EXPERTS 512 // Qwen3 Next +#define LLAMA_MAX_EXPERTS 1024 // Kimi-K3 enum llama_expert_gating_func_type { LLAMA_EXPERT_GATING_FUNC_TYPE_NONE = 0,