Georgi Gerganov 6fdddb4987 metal : support virtual devices (#18919) ...

* metal : support virtual devices

* cont : manage buffer type context memory

* metal : add events

* cont : implement cpy_tensor_async

2026-02-02 14:29:44 +02:00

..

models

docs : Minor cleanups (#19252)

2026-02-02 08:38:55 +02:00

CMakeLists.txt

memory : add llama_memory_hybrid_iswa (#18601)

2026-01-21 14:30:23 +02:00

llama-adapter.cpp

lora: make sure model keep track of associated adapters (#18490)

2026-01-15 10:24:28 +01:00

llama-adapter.h

lora: make sure model keep track of associated adapters (#18490)

2026-01-15 10:24:28 +01:00

llama-arch.cpp

…

llama-arch.h

…

llama-batch.cpp

…

llama-batch.h

…

llama-chat.cpp

docs : Minor cleanups (#19252)

2026-02-02 08:38:55 +02:00

llama-chat.h

…

llama-context.cpp

metal : support virtual devices (#18919)

2026-02-02 14:29:44 +02:00

llama-context.h

sampling : remove sampling branching in output_reserve (#18811)

2026-01-28 05:59:30 +01:00

llama-cparams.cpp

…

llama-cparams.h

context : reserve new scheduler when graph topology changes (#18547)

2026-01-15 16:39:17 +02:00

llama-grammar.cpp

…

llama-grammar.h

…

llama-graph.cpp

cuda : fix nkvo, offload and cuda graph node properties matching (#19165)

2026-01-29 18:45:30 +02:00

llama-graph.h

kv-cache : support V-less cache (#19067)

2026-01-25 15:48:56 +02:00

llama-hparams.cpp

kv-cache : support V-less cache (#19067)

2026-01-25 15:48:56 +02:00

llama-hparams.h

docs : Minor cleanups (#19252)

2026-02-02 08:38:55 +02:00

llama-impl.cpp

…

llama-impl.h

…

llama-io.cpp

…

llama-io.h

…

llama-kv-cache-iswa.cpp

…

llama-kv-cache-iswa.h

…

llama-kv-cache.cpp

memory : remove unused tmp_buf (#19199)

2026-01-30 10:37:06 +01:00

llama-kv-cache.h

kv-cache : optimize KQ mask construction (#18842)

2026-01-17 15:42:42 +02:00

llama-kv-cells.h

…

llama-memory-hybrid-iswa.cpp

memory : add llama_memory_hybrid_iswa (#18601)

2026-01-21 14:30:23 +02:00

llama-memory-hybrid-iswa.h

memory : add llama_memory_hybrid_iswa (#18601)

2026-01-21 14:30:23 +02:00

llama-memory-hybrid.cpp

…

llama-memory-hybrid.h

…

llama-memory-recurrent.cpp

memory : clarify comments for r_l and s_l tensors [no ci] (#19203)

2026-01-30 15:18:41 +01:00

llama-memory-recurrent.h

…

llama-memory.cpp

…

llama-memory.h

…

llama-mmap.cpp

llama : Extend fallback, fix fileno for dio file, exclude case that mmap uses dio file (#18887)

2026-01-18 18:35:57 +02:00

llama-mmap.h

…

llama-model-loader.cpp

llama : disable Direct IO by default (#19109)

2026-01-28 09:11:13 +02:00

llama-model-loader.h

…

llama-model-saver.cpp

kv-cache : support V-less cache (#19067)

2026-01-25 15:48:56 +02:00

llama-model-saver.h

…

llama-model.cpp

llama : disable Direct IO by default (#19109)

2026-01-28 09:11:13 +02:00

llama-model.h

lora: make sure model keep track of associated adapters (#18490)

2026-01-15 10:24:28 +01:00

llama-quant.cpp

llama : disable Direct IO by default (#19109)

2026-01-28 09:11:13 +02:00

llama-quant.h

…

llama-sampling.cpp

llama : add adaptive-p sampler (#17927)

2026-01-15 19:16:29 +02:00

llama-sampling.h

…

llama-vocab.cpp

docs : Minor cleanups (#19252)

2026-02-02 08:38:55 +02:00

llama-vocab.h

…

llama.cpp

llama: fix integer type consistency in split helpers (#18894)

2026-01-25 09:10:52 +02:00

unicode-data.cpp

…

unicode-data.h

…

unicode.cpp

…

unicode.h

…