Kawrakow ada5cc1523 Fused norm (#1086) ...

* Adding fused_norm - same idea as fused_rms_norm

* Avoid computing the attention reduce op for cohere2

---------

Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>

2025-12-24 15:22:43 +01:00

..

ggml-alloc.h

Merge mainline llama.cpp (#3)

2024-07-27 07:55:01 +02:00

ggml-backend.h

Better PP performance with split mode "graph" and 3+ GPUs (#1069)

2025-12-17 07:40:25 +01:00

ggml-blas.h

Merge mainline llama.cpp (#3)

2024-07-27 07:55:01 +02:00

ggml-cann.h

Merge mainline llama.cpp (#3)

2024-07-27 07:55:01 +02:00

ggml-cpp.h

Port mdmd from mainline + Qwen2/2.5-VL support (#798)

2025-09-27 08:45:29 +02:00

ggml-cuda.h

CUDA: set compute parameters via command line arguments (#910)

2025-11-07 07:11:23 +02:00

ggml-kompute.h

Merge mainline llama.cpp (#3)

2024-07-27 07:55:01 +02:00

ggml-metal.h

Merge mainline - Aug 12 2024 (#17)

2024-08-12 15:14:32 +02:00

ggml-rpc.h

RPC: support multiple devices including cpu (#1024)

2025-11-30 18:48:02 +01:00

ggml-sycl.h

Merge mainline llama.cpp (#3)

2024-07-27 07:55:01 +02:00

ggml-vulkan.h

Vulkan: a fresh start (#608)

2025-07-15 08:03:13 +02:00

ggml.h

Fused norm (#1086)

2025-12-24 15:22:43 +01:00