public_git
/
whisper.cpp
mirror of https://github.com/ggml-org/whisper.cpp.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

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 <ggerganov@gmail.com>
Co-authored-by: Matt Clayton <156335168+mattjcly@users.noreply.github.com>
This commit is contained in:
Daniel Bevenius 2026-03-11 19:27:53 +01:00 committed by Georgi Gerganov
parent e2aa5c73f3
commit 5d3a5447c8
1 changed files with 1 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
ggml/src/ggml-metal/ggml-metal.metal
View File

@ -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(