Weizhao Ouyang 566c16fcce model : add support for ERNIE 4.5 0.3B model (#14408) ...

Add Day-0 support for Baidu ERNIE 4.5 0.3B model.

Signed-off-by: Weizhao Ouyang <[email protected]>

2025-06-28 16:08:21 +02:00

..

CMakeLists.txt

…

llama-adapter.cpp

…

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

…

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

…

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

…

llama-cparams.h

…

llama-grammar.cpp

…

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

…

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

…

llama-memory.h

memory : rename interface to llama_memory_context_i (#14296)

2025-06-21 08:03:46 +03:00

llama-mmap.cpp

…

llama-mmap.h

…

llama-model-loader.cpp

…

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-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

…

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

…

unicode-data.cpp

…

unicode-data.h

…

unicode.cpp

…

unicode.h

…