| .. |
|
CMakeLists.txt
|
381603a775
ci: detach common from the library (#12827)
|
преди 9 месеца |
|
llama-adapter.cpp
|
f28bc4c286
llama : make loras compatible with repacking (#12593)
|
преди 9 месеца |
|
llama-adapter.h
|
e0dbec0bc6
llama : refactor llama_context, llama_kv_cache, llm_build_context (#12181)
|
преди 10 месеца |
|
llama-arch.cpp
|
daa422881a
llama : DeepSeek V2/V3 MLA implementation (#12801)
|
преди 9 месеца |
|
llama-arch.h
|
daa422881a
llama : DeepSeek V2/V3 MLA implementation (#12801)
|
преди 9 месеца |
|
llama-batch.cpp
|
f66f582927
llama : refactor `src/llama.cpp` (#10902)
|
преди 1 година |
|
llama-batch.h
|
e0dbec0bc6
llama : refactor llama_context, llama_kv_cache, llm_build_context (#12181)
|
преди 10 месеца |
|
llama-chat.cpp
|
1466621e73
llama : Support llama 4 text-only (#12791)
|
преди 9 месеца |
|
llama-chat.h
|
1466621e73
llama : Support llama 4 text-only (#12791)
|
преди 9 месеца |
|
llama-context.cpp
|
daa422881a
llama : DeepSeek V2/V3 MLA implementation (#12801)
|
преди 9 месеца |
|
llama-context.h
|
8fcb563613
Load all MoE experts during warmup (#11571)
|
преди 10 месеца |
|
llama-cparams.cpp
|
f66f582927
llama : refactor `src/llama.cpp` (#10902)
|
преди 1 година |
|
llama-cparams.h
|
8fcb563613
Load all MoE experts during warmup (#11571)
|
преди 10 месеца |
|
llama-grammar.cpp
|
669912d9a5
`tool-call`: fix Qwen 2.5 Coder support, add micro benchmarks, support trigger patterns for lazy grammars (#12034)
|
преди 10 месеца |
|
llama-grammar.h
|
669912d9a5
`tool-call`: fix Qwen 2.5 Coder support, add micro benchmarks, support trigger patterns for lazy grammars (#12034)
|
преди 10 месеца |
|
llama-graph.cpp
|
daa422881a
llama : DeepSeek V2/V3 MLA implementation (#12801)
|
преди 9 месеца |
|
llama-graph.h
|
daa422881a
llama : DeepSeek V2/V3 MLA implementation (#12801)
|
преди 9 месеца |
|
llama-hparams.cpp
|
081bee8c64
hparams : add SWA rope parameters (#12374)
|
преди 10 месеца |
|
llama-hparams.h
|
daa422881a
llama : DeepSeek V2/V3 MLA implementation (#12801)
|
преди 9 месеца |
|
llama-impl.cpp
|
53ff6b9b9f
GGUF: C++ refactor, backend support, misc fixes (#11030)
|
преди 1 година |
|
llama-impl.h
|
fef0cbeadf
cleanup: fix compile warnings associated with gnu_printf (#11811)
|
преди 11 месеца |
|
llama-io.cpp
|
e0dbec0bc6
llama : refactor llama_context, llama_kv_cache, llm_build_context (#12181)
|
преди 10 месеца |
|
llama-io.h
|
e0dbec0bc6
llama : refactor llama_context, llama_kv_cache, llm_build_context (#12181)
|
преди 10 месеца |
|
llama-kv-cache.cpp
|
daa422881a
llama : DeepSeek V2/V3 MLA implementation (#12801)
|
преди 9 месеца |
|
llama-kv-cache.h
|
3e1d29348b
kv-cache : simplify + fix warning for recurrent models (#12756)
|
преди 9 месеца |
|
llama-memory.cpp
|
e0dbec0bc6
llama : refactor llama_context, llama_kv_cache, llm_build_context (#12181)
|
преди 10 месеца |
|
llama-memory.h
|
3e1d29348b
kv-cache : simplify + fix warning for recurrent models (#12756)
|
преди 9 месеца |
|
llama-mmap.cpp
|
c54f6b7988
mmap : skip resource limit checks on AIX (#12541)
|
преди 9 месеца |
|
llama-mmap.h
|
19b392d58d
llama-mmap: fix missing include (#11796)
|
преди 11 месеца |
|
llama-model-loader.cpp
|
833e2b7409
model : print tensor size during load (#12711)
|
преди 9 месеца |
|
llama-model-loader.h
|
e0e912f49b
llama : add option to override model tensor buffers (#11397)
|
преди 9 месеца |
|
llama-model.cpp
|
daa422881a
llama : DeepSeek V2/V3 MLA implementation (#12801)
|
преди 9 месеца |
|
llama-model.h
|
daa422881a
llama : DeepSeek V2/V3 MLA implementation (#12801)
|
преди 9 месеца |
|
llama-quant.cpp
|
71e90e8813
quantize: Handle user-defined quantization levels for additional tensors (#12511)
|
преди 9 месеца |
|
llama-quant.h
|
f66f582927
llama : refactor `src/llama.cpp` (#10902)
|
преди 1 година |
|
llama-sampling.cpp
|
dd373dd3bf
llama: fix error on bad grammar (#12628)
|
преди 9 месеца |
|
llama-sampling.h
|
afa8a9ec9b
llama : add `llama_vocab`, functions -> methods, naming (#11110)
|
преди 1 година |
|
llama-vocab.cpp
|
06bb53ad9b
llama-model : add Glm4Model implementation for GLM-4-0414 (#12867)
|
преди 9 месеца |
|
llama-vocab.h
|
08f10f69c3
llama : remove notion of CLS token (#11064)
|
преди 1 година |
|
llama.cpp
|
e0e912f49b
llama : add option to override model tensor buffers (#11397)
|
преди 9 месеца |
|
unicode-data.cpp
|
458367a906
server : better security control for public deployments (#9776)
|
преди 1 година |
|
unicode-data.h
|
a39ab216aa
llama : reduce compile time and binary size (#9712)
|
преди 1 година |
|
unicode.cpp
|
68ff663a04
repo : update links to new url (#11886)
|
преди 11 месеца |
|
unicode.h
|
08ea539df2
unicode : improve naming style (#10838)
|
преди 1 година |
Juk Armstrong
daa422881a
llama : DeepSeek V2/V3 MLA implementation (#12801)