From: Daniel Bevenius <redacted>
Date: Wed, 11 Mar 2026 18:27:53 +0000 (+0100)
Subject: llama : add support for Nemotron 3 Super (llama/20411)
X-Git-Tag: upstream/1.8.4~49
X-Git-Url: https://git.djapps.eu/?a=commitdiff_plain;h=5d3a5447c8e50a59149a08392d487b8eea6e73c3;p=pkg%2Fggml%2Fsources%2Fwhisper.cpp

llama : add support for Nemotron 3 Super (llama/20411)

* llama : add support for Nemotron 3 Super

This commit adds support for the Nemotron 3 Super model (120B.A12B)
enabling this model to be converted to GGUF format and run in llama.cpp.

Co-authored-by: Georgi Gerganov <redacted>
Co-authored-by: Matt Clayton <redacted>
---

diff --git a/ggml/src/ggml-metal/ggml-metal.metal b/ggml/src/ggml-metal/ggml-metal.metal
index 82ebbb4e..29e4a245 100644
--- a/ggml/src/ggml-metal/ggml-metal.metal
+++ b/ggml/src/ggml-metal/ggml-metal.metal
@@ -9081,6 +9081,7 @@ template [[host_name("kernel_mul_mm_id_map0_ne20_6" )]] kernel kernel_mul_mm_id_
 template [[host_name("kernel_mul_mm_id_map0_ne20_8" )]] kernel kernel_mul_mm_id_map0_t kernel_mul_mm_id_map0<8>;
 template [[host_name("kernel_mul_mm_id_map0_ne20_10")]] kernel kernel_mul_mm_id_map0_t kernel_mul_mm_id_map0<10>;
 template [[host_name("kernel_mul_mm_id_map0_ne20_16")]] kernel kernel_mul_mm_id_map0_t kernel_mul_mm_id_map0<16>;
+template [[host_name("kernel_mul_mm_id_map0_ne20_22")]] kernel kernel_mul_mm_id_map0_t kernel_mul_mm_id_map0<22>;
 
 template<typename S0, typename S0_4x4, typename S0_8x8, typename S1, typename S1_2x4, typename S1_8x8, typename block_q, short nl, void (*dequantize_func)(device const block_q *, short, thread S0_4x4 &), typename T0, typename T0_4x4, typename T1, typename T1_2x4>
 kernel void kernel_mul_mm_id(