Xuan-Son Nguyen 3e3cb19f64 llama-quant: add support for mmproj (#16592) ...

* llama-quant: add support for mmproj

* Update src/llama.cpp

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

* check prefix instead

* small fix

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

2025-10-15 14:48:08 +02:00

..

CMakeLists.txt

…

llama-adapter.cpp

…

llama-adapter.h

…

llama-arch.cpp

llama-quant: add support for mmproj (#16592)

2025-10-15 14:48:08 +02:00

llama-arch.h

llama-quant: add support for mmproj (#16592)

2025-10-15 14:48:08 +02:00

llama-batch.cpp

…

llama-batch.h

…

llama-chat.cpp

chat : Granite Docling stopping (#16438)

2025-10-06 18:59:40 +02:00

llama-chat.h

model : add grok-2 support (#15539)

2025-09-14 23:00:59 +02:00

llama-context.cpp

model: EmbeddingGemma Adding Support for SentenceTransformers Dense Modules (#16367)

2025-10-09 09:39:18 +03:00

llama-context.h

llama: print memory breakdown on exit (#15860)

2025-09-24 16:53:48 +02:00

llama-cparams.cpp

…

llama-cparams.h

llama : bump max seq limit from 64 to 256 (#15916)

2025-09-18 12:47:56 +03:00

llama-grammar.cpp

…

llama-grammar.h

…

llama-graph.cpp

metal : FA support F32 K and V and head size = 32 (#16531)

2025-10-13 23:07:57 +03:00

llama-graph.h

graph : support cacheless embeddings with FA and iSWA (#16528)

2025-10-13 22:42:37 +03:00

llama-hparams.cpp

hparams : add check for layer index in is_recurrent (#16511)

2025-10-12 07:19:06 +02:00

llama-hparams.h

model: EmbeddingGemma Adding Support for SentenceTransformers Dense Modules (#16367)

2025-10-09 09:39:18 +03:00

llama-impl.cpp

…

llama-impl.h

…

llama-io.cpp

…

llama-io.h

…

llama-kv-cache-iswa.cpp

server : context checkpointing for hybrid and recurrent models (#16382)

2025-10-03 21:34:51 +03:00

llama-kv-cache-iswa.h

llama: print memory breakdown on exit (#15860)

2025-09-24 16:53:48 +02:00

llama-kv-cache.cpp

server : host-memory prompt caching (#16391)

2025-10-09 18:54:51 +03:00

llama-kv-cache.h

llama: print memory breakdown on exit (#15860)

2025-09-24 16:53:48 +02:00

llama-kv-cells.h

…

llama-memory-hybrid.cpp

memory : use sequential equal splits for recurrent modules (#16442)

2025-10-07 08:24:17 +03:00

llama-memory-hybrid.h

llama: print memory breakdown on exit (#15860)

2025-09-24 16:53:48 +02:00

llama-memory-recurrent.cpp

server : improve context checkpoint logic (#16440)

2025-10-08 10:57:29 +03:00

llama-memory-recurrent.h

llama: print memory breakdown on exit (#15860)

2025-09-24 16:53:48 +02:00

llama-memory.cpp

…

llama-memory.h

llama: print memory breakdown on exit (#15860)

2025-09-24 16:53:48 +02:00

llama-mmap.cpp

…

llama-mmap.h

…

llama-model-loader.cpp

model : Apertus model implementation (#15852)

2025-10-02 20:43:22 +03:00

llama-model-loader.h

…

llama-model-saver.cpp

…

llama-model-saver.h

…

llama-model.cpp

llama-quant: add support for mmproj (#16592)

2025-10-15 14:48:08 +02:00

llama-model.h

model: EmbeddingGemma Adding Support for SentenceTransformers Dense Modules (#16367)

2025-10-09 09:39:18 +03:00

llama-quant.cpp

llama-quant: add support for mmproj (#16592)

2025-10-15 14:48:08 +02:00

llama-quant.h

…

llama-sampling.cpp

vocab : mark EOT token for Granite models (#16499)

2025-10-10 17:17:31 +03:00

llama-sampling.h

…

llama-vocab.cpp

vocab : mark EOT token for Granite models (#16499)

2025-10-10 17:17:31 +03:00

llama-vocab.h

model : Granite docling + Idefics3 preprocessing (SmolVLM) (#16206)

2025-10-05 14:57:47 +02:00

llama.cpp

llama-quant: add support for mmproj (#16592)

2025-10-15 14:48:08 +02:00

unicode-data.cpp

…

unicode-data.h

…

unicode.cpp

…

unicode.h

devops: add s390x & ppc64le CI (#15925)

2025-09-27 02:03:33 +08:00