| .. |
|
CMakeLists.txt
|
memory : Hybrid recurrent cache (#13979)
|
2025-06-19 08:08:14 +03:00 |
|
llama-adapter.cpp
|
llama : do not crash if there is no CPU backend (#13395)
|
2025-05-09 13:02:07 +02:00 |
|
llama-adapter.h
|
|
|
|
llama-arch.cpp
|
model : add support for ERNIE 4.5 0.3B model (#14408)
|
2025-06-28 16:08:21 +02:00 |
|
llama-arch.h
|
model : add support for ERNIE 4.5 0.3B model (#14408)
|
2025-06-28 16:08:21 +02:00 |
|
llama-batch.cpp
|
batch : fix check for empty sequences in memory (#14364)
|
2025-06-24 18:26:30 +03:00 |
|
llama-batch.h
|
ubatch : new splitting logic (#14217)
|
2025-06-20 10:14:14 +03:00 |
|
llama-chat.cpp
|
llama : better rwkv chat template and add missing inputs.use_jinja setting (#14336)
|
2025-06-23 19:56:19 +08:00 |
|
llama-chat.h
|
model : add dots.llm1 architecture support (#14044) (#14118)
|
2025-06-15 09:52:06 +02:00 |
|
llama-context.cpp
|
kv-cells : fix tracking of seq_pos (#14339)
|
2025-06-23 12:27:35 +03:00 |
|
llama-context.h
|
memory : rename interface to llama_memory_context_i (#14296)
|
2025-06-21 08:03:46 +03:00 |
|
llama-cparams.cpp
|
cparams : rename LLAMA_MAX_PARALLEL_SEQUENCES to LLAMA_MAX_SEQ (#14188)
|
2025-06-15 10:08:58 +03:00 |
|
llama-cparams.h
|
cparams : rename LLAMA_MAX_PARALLEL_SEQUENCES to LLAMA_MAX_SEQ (#14188)
|
2025-06-15 10:08:58 +03:00 |
|
llama-grammar.cpp
|
server: streaming of tool calls and thoughts when --jinja is on (#12379)
|
2025-05-25 01:48:08 +01:00 |
|
llama-grammar.h
|
|
|
|
llama-graph.cpp
|
model : gemma3n text-only (#14400)
|
2025-06-26 20:34:02 +03:00 |
|
llama-graph.h
|
graph : make llm_graph_context destructor virtual (#14410)
|
2025-06-27 21:42:02 +03:00 |
|
llama-hparams.cpp
|
ubatch : new splitting logic (#14217)
|
2025-06-20 10:14:14 +03:00 |
|
llama-hparams.h
|
model : gemma3n text-only (#14400)
|
2025-06-26 20:34:02 +03:00 |
|
llama-impl.cpp
|
|
|
|
llama-impl.h
|
|
|
|
llama-io.cpp
|
|
|
|
llama-io.h
|
|
|
|
llama-kv-cache-unified-iswa.cpp
|
memory : rename interface to llama_memory_context_i (#14296)
|
2025-06-21 08:03:46 +03:00 |
|
llama-kv-cache-unified-iswa.h
|
memory : rename interface to llama_memory_context_i (#14296)
|
2025-06-21 08:03:46 +03:00 |
|
llama-kv-cache-unified.cpp
|
model : gemma3n text-only (#14400)
|
2025-06-26 20:34:02 +03:00 |
|
llama-kv-cache-unified.h
|
memory : rename interface to llama_memory_context_i (#14296)
|
2025-06-21 08:03:46 +03:00 |
|
llama-kv-cells.h
|
kv-cells : fix tracking of seq_pos (#14339)
|
2025-06-23 12:27:35 +03:00 |
|
llama-memory-hybrid.cpp
|
memory : rename interface to llama_memory_context_i (#14296)
|
2025-06-21 08:03:46 +03:00 |
|
llama-memory-hybrid.h
|
memory : rename interface to llama_memory_context_i (#14296)
|
2025-06-21 08:03:46 +03:00 |
|
llama-memory-recurrent.cpp
|
recurrent : call balloc split_reset() in init_batch() (#14414)
|
2025-06-27 17:55:45 +03:00 |
|
llama-memory-recurrent.h
|
memory : rename interface to llama_memory_context_i (#14296)
|
2025-06-21 08:03:46 +03:00 |
|
llama-memory.cpp
|
kv-cache : refactor the update/defrag mechanism (#13988)
|
2025-06-04 18:58:20 +03:00 |
|
llama-memory.h
|
memory : rename interface to llama_memory_context_i (#14296)
|
2025-06-21 08:03:46 +03:00 |
|
llama-mmap.cpp
|
llama : allow using mmap without PrefetchVirtualMemory, apply GGML_WIN_VER to llama.cpp sources (#14013)
|
2025-06-05 11:57:42 +02:00 |
|
llama-mmap.h
|
|
|
|
llama-model-loader.cpp
|
llama : support multiple classifier outputs and labels (#13940)
|
2025-06-06 09:03:25 +02:00 |
|
llama-model-loader.h
|
|
|
|
llama-model-saver.cpp
|
llama : improve sep token handling (#14272)
|
2025-06-20 14:04:09 +02:00 |
|
llama-model-saver.h
|
llama/ggml: add LLM training support (#10544)
|
2025-05-12 14:44:49 +02:00 |
|
llama-model.cpp
|
model : add support for ERNIE 4.5 0.3B model (#14408)
|
2025-06-28 16:08:21 +02:00 |
|
llama-model.h
|
model : add support for ERNIE 4.5 0.3B model (#14408)
|
2025-06-28 16:08:21 +02:00 |
|
llama-quant.cpp
|
model : gemma3n text-only (#14400)
|
2025-06-26 20:34:02 +03:00 |
|
llama-quant.h
|
|
|
|
llama-sampling.cpp
|
sampling : make sure samplers return at least 1 token (#13822)
|
2025-05-27 12:07:52 +03:00 |
|
llama-sampling.h
|
|
|
|
llama-vocab.cpp
|
lint : remove trailing whitepace (#14304)
|
2025-06-20 16:37:44 +02:00 |
|
llama-vocab.h
|
llama : improve sep token handling (#14272)
|
2025-06-20 14:04:09 +02:00 |
|
llama.cpp
|
llama : add thread safety test (#14035)
|
2025-06-16 08:11:43 -07:00 |
|
unicode-data.cpp
|
|
|
|
unicode-data.h
|
|
|
|
unicode.cpp
|
build : suppress gcc15 compile warnings (#14261)
|
2025-06-19 14:49:48 +02:00 |
|
unicode.h
|
|
|
566c16fcce