Daniel Hiltgen 0cf7794b16 ggml update to b7108 (#12992) ...

* Revert "vulkan: temporary cary of vulkan fixes (#12971)"

This reverts commit 3a9e8e9fd4.

* ggml update to b7087

* fix argsort on metal

* update to b7108

* fix bakllava regression

This model lacks the metadata for the projector type.

* update to b7209

* fix TopK perf

* only build arm code on arm

2025-12-03 19:43:29 -08:00

..

models

ggml update to b7108 (#12992)

2025-12-03 19:43:29 -08:00

llama-adapter.cpp

Update GGML to b6646 (#12245)

2025-10-02 14:47:10 -07:00

llama-adapter.h

Update GGML to b6646 (#12245)

2025-10-02 14:47:10 -07:00

llama-arch.cpp

ggml update to b7108 (#12992)

2025-12-03 19:43:29 -08:00

llama-arch.h

ggml update to b7108 (#12992)

2025-12-03 19:43:29 -08:00

llama-batch.cpp

ggml update to b7108 (#12992)

2025-12-03 19:43:29 -08:00

llama-batch.h

ggml update to b7108 (#12992)

2025-12-03 19:43:29 -08:00

llama-chat.cpp

ggml update to b7108 (#12992)

2025-12-03 19:43:29 -08:00

llama-chat.h

ggml update to b7108 (#12992)

2025-12-03 19:43:29 -08:00

llama-context.cpp

ggml update to b7108 (#12992)

2025-12-03 19:43:29 -08:00

llama-context.h

ggml update to b7108 (#12992)

2025-12-03 19:43:29 -08:00

llama-cparams.cpp

update vendored llama.cpp and ggml (#11823)

2025-08-14 14:42:58 -07:00

llama-cparams.h

ggml update to b7108 (#12992)

2025-12-03 19:43:29 -08:00

llama-grammar.cpp

ggml update to b7108 (#12992)

2025-12-03 19:43:29 -08:00

llama-grammar.h

llama: remove model loading for grammar (#10096)

2025-04-24 11:51:19 -07:00

llama-graph.cpp

ggml update to b7108 (#12992)

2025-12-03 19:43:29 -08:00

llama-graph.h

ggml update to b6840 (#12791)

2025-11-06 10:19:22 -08:00

llama-hparams.cpp

ggml update to b7108 (#12992)

2025-12-03 19:43:29 -08:00

llama-hparams.h

ggml update to b7108 (#12992)

2025-12-03 19:43:29 -08:00

llama-impl.cpp

ggml update to b7108 (#12992)

2025-12-03 19:43:29 -08:00

llama-impl.h

Update GGML to b6646 (#12245)

2025-10-02 14:47:10 -07:00

llama-io.cpp

llama: update to commit 71e90e88 (#10192)

2025-04-16 15:14:01 -07:00

llama-io.h

llama: update to commit 71e90e88 (#10192)

2025-04-16 15:14:01 -07:00

llama-kv-cache-iswa.cpp

ggml update to b7108 (#12992)

2025-12-03 19:43:29 -08:00

llama-kv-cache-iswa.h

Update GGML to b6646 (#12245)

2025-10-02 14:47:10 -07:00

llama-kv-cache.cpp

ggml update to b7108 (#12992)

2025-12-03 19:43:29 -08:00

llama-kv-cache.h

ggml update to b7108 (#12992)

2025-12-03 19:43:29 -08:00

llama-kv-cells.h

ggml update to b7108 (#12992)

2025-12-03 19:43:29 -08:00

llama-memory-hybrid.cpp

Llama cpp bump (df1b612): granite docling / mamba2 optimizations / multimodal encoding fixes (#12552)

2025-10-13 15:26:18 -07:00

llama-memory-hybrid.h

Update GGML to b6646 (#12245)

2025-10-02 14:47:10 -07:00

llama-memory-recurrent.cpp

ggml update to b7108 (#12992)

2025-12-03 19:43:29 -08:00

llama-memory-recurrent.h

ggml update to b7108 (#12992)

2025-12-03 19:43:29 -08:00

llama-memory.cpp

update vendored llama.cpp and ggml (#11823)

2025-08-14 14:42:58 -07:00

llama-memory.h

Update GGML to b6646 (#12245)

2025-10-02 14:47:10 -07:00

llama-mmap.cpp

update vendored llama.cpp and ggml (#11823)

2025-08-14 14:42:58 -07:00

llama-mmap.h

llama: update llama.cpp vendor code to commit d7cfe1ff (#9356)

2025-02-26 20:34:44 -08:00

llama-model-loader.cpp

Llama cpp bump (df1b612): granite docling / mamba2 optimizations / multimodal encoding fixes (#12552)

2025-10-13 15:26:18 -07:00

llama-model-loader.h

update vendored llama.cpp and ggml (#11823)

2025-08-14 14:42:58 -07:00

llama-model-saver.cpp

update vendored llama.cpp and ggml (#11823)

2025-08-14 14:42:58 -07:00

llama-model-saver.h

llama: update to commit de4c07f93 (#10655)

2025-05-12 12:17:26 -07:00

llama-model.cpp

ggml update to b7108 (#12992)

2025-12-03 19:43:29 -08:00

llama-model.h

ggml update to b7108 (#12992)

2025-12-03 19:43:29 -08:00

llama-quant.cpp

ggml update to b7108 (#12992)

2025-12-03 19:43:29 -08:00

llama-quant.h

next build (#8539)

2025-01-29 15:03:38 -08:00

llama-sampling.cpp

ggml update to b7108 (#12992)

2025-12-03 19:43:29 -08:00

llama-sampling.h

llama: update llama.cpp vendor code to commit d7cfe1ff (#9356)

2025-02-26 20:34:44 -08:00

llama-vocab.cpp

ggml update to b7108 (#12992)

2025-12-03 19:43:29 -08:00

llama-vocab.h

ggml update to b7108 (#12992)

2025-12-03 19:43:29 -08:00

llama.cpp

ggml update to b6840 (#12791)

2025-11-06 10:19:22 -08:00

llama.go

ggml update to b7108 (#12992)

2025-12-03 19:43:29 -08:00

unicode-data.cpp

next build (#8539)

2025-01-29 15:03:38 -08:00

unicode-data.h

next build (#8539)

2025-01-29 15:03:38 -08:00

unicode.cpp

ggml update to b7108 (#12992)

2025-12-03 19:43:29 -08:00

unicode.h

Update GGML to b6646 (#12245)

2025-10-02 14:47:10 -07:00