Kawrakow b50efcc9d2 Fused MoE ffn_up and ffn_gate (#229) ...

* Fusing MoE up * unary(gate)

* Fusing MoE up * unary(gate): CUDA

We get ~13% speedup for PP-512 and ~2% for TG-128
for DeepSeek-Lite

* On CUDA also fuse MoE down * (up * unary(gate))

in case the MUL_MAT_ID op for the down experts is the next
op in the graph.

* Command line option to enable fused MoE up*unary(gate)

* Add fmoe option to llama-bench

* Adding forgotten gelu, relu, silu on ARM

---------

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

2025-02-23 14:31:11 +02:00

..

cmake

Merge mainline llama.cpp (#3)

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

base64.hpp

llava : expose as a shared library for downstream projects (#3613)

2023-11-07 00:36:23 +03:00

build-info.cpp.in

build : link against build info instead of compiling against it (#3879)

2023-11-02 08:50:16 +02:00

CMakeLists.txt

Merge mainline llama.cpp (#3)

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

common.cpp

Fused MoE ffn_up and ffn_gate (#229)

2025-02-23 14:31:11 +02:00

common.h

Fused MoE ffn_up and ffn_gate (#229)

2025-02-23 14:31:11 +02:00

console.cpp

check C++ code with -Wmissing-declarations (#3184)

2023-09-15 15:38:27 -04:00

console.h

gguf : new file format with flexible meta data (beta) (#2398)

2023-08-21 23:07:43 +03:00

grammar-parser.cpp

Added support for . (any character) token in grammar engine. (#6467)

2024-06-06 06:08:52 -07:00

grammar-parser.h

gguf : new file format with flexible meta data (beta) (#2398)

2023-08-21 23:07:43 +03:00

json-schema-to-grammar.cpp

Merge mainline llama.cpp (#3)

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

json-schema-to-grammar.h

JSON: [key] -> .at(key), assert() -> GGML_ASSERT (#7143)

2024-05-08 21:53:08 +02:00

json.hpp

json-schema-to-grammar improvements (+ added to server) (#5978)

2024-03-21 11:50:43 +00:00

log.h

Merge mainline llama.cpp (#3)

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

ngram-cache.cpp

Fixed lookup compilation issues on Windows (#6273)

2024-03-24 14:21:17 +01:00

ngram-cache.h

Merge mainline llama.cpp (#3)

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

sampling.cpp

Merge mainline llama.cpp (#3)

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

sampling.h

common : normalize naming style (#7462)

2024-05-22 20:04:20 +03:00

stb_image.h

examples: support LLaVA v1.5 (multimodal model) (#3436)

2023-10-12 18:23:18 +03:00

train.cpp

train : change default FA argument (#7528)

2024-05-25 15:22:35 +03:00

train.h

sync : ggml (backend v2) (#3912)

2023-11-13 14:16:23 +02:00