| .. |
|
CMakeLists.txt
|
10d2af0eaa
llama/ggml: add LLM training support (#10544)
|
8 mesi fa |
|
llama-adapter.cpp
|
27ebfcacba
llama : do not crash if there is no CPU backend (#13395)
|
8 mesi fa |
|
llama-adapter.h
|
e0dbec0bc6
llama : refactor llama_context, llama_kv_cache, llm_build_context (#12181)
|
10 mesi fa |
|
llama-arch.cpp
|
d590cd4c24
model : Granite MoE shared (#13269)
|
8 mesi fa |
|
llama-arch.h
|
5f5e39e1ba
model : Nomic Embed Text V2 with Mixture-of-Experts (MoE) architecture (#12466)
|
8 mesi fa |
|
llama-batch.cpp
|
c642bc014c
kv-cache : separate recurrent vs non-recurrent impl (#12799)
|
8 mesi fa |
|
llama-batch.h
|
c642bc014c
kv-cache : separate recurrent vs non-recurrent impl (#12799)
|
8 mesi fa |
|
llama-chat.cpp
|
3f96aeff39
llama : one-off chat template fix for Mistral-Small-2503 (#13398)
|
8 mesi fa |
|
llama-chat.h
|
3f96aeff39
llama : one-off chat template fix for Mistral-Small-2503 (#13398)
|
8 mesi fa |
|
llama-context.cpp
|
a4090d1174
llama : remove llama_kv_cache_view API + remove deprecated (#13653)
|
8 mesi fa |
|
llama-context.h
|
10d2af0eaa
llama/ggml: add LLM training support (#10544)
|
8 mesi fa |
|
llama-cparams.cpp
|
f66f582927
llama : refactor `src/llama.cpp` (#10902)
|
1 anno fa |
|
llama-cparams.h
|
7f323a589f
Add `--no-op-offload` to improve `-ot` pp perf in MoE models like llama4 400B (#13386)
|
8 mesi fa |
|
llama-grammar.cpp
|
669912d9a5
`tool-call`: fix Qwen 2.5 Coder support, add micro benchmarks, support trigger patterns for lazy grammars (#12034)
|
10 mesi fa |
|
llama-grammar.h
|
669912d9a5
`tool-call`: fix Qwen 2.5 Coder support, add micro benchmarks, support trigger patterns for lazy grammars (#12034)
|
10 mesi fa |
|
llama-graph.cpp
|
c9c64dee57
Set GLM4 blk.*.attn_output.weight, kqv_out-* matmul to GGML_PREC_F32 to fix infinity values in output (#13639)
|
8 mesi fa |
|
llama-graph.h
|
e298d2fbd0
kv-cache : add SWA support (#13194)
|
8 mesi fa |
|
llama-hparams.cpp
|
081bee8c64
hparams : add SWA rope parameters (#12374)
|
10 mesi fa |
|
llama-hparams.h
|
e298d2fbd0
kv-cache : add SWA support (#13194)
|
8 mesi fa |
|
llama-impl.cpp
|
53ff6b9b9f
GGUF: C++ refactor, backend support, misc fixes (#11030)
|
1 anno fa |
|
llama-impl.h
|
fef0cbeadf
cleanup: fix compile warnings associated with gnu_printf (#11811)
|
11 mesi fa |
|
llama-io.cpp
|
e0dbec0bc6
llama : refactor llama_context, llama_kv_cache, llm_build_context (#12181)
|
10 mesi fa |
|
llama-io.h
|
e0dbec0bc6
llama : refactor llama_context, llama_kv_cache, llm_build_context (#12181)
|
10 mesi fa |
|
llama-kv-cache.cpp
|
a4090d1174
llama : remove llama_kv_cache_view API + remove deprecated (#13653)
|
8 mesi fa |
|
llama-kv-cache.h
|
a4090d1174
llama : remove llama_kv_cache_view API + remove deprecated (#13653)
|
8 mesi fa |
|
llama-memory.cpp
|
e0dbec0bc6
llama : refactor llama_context, llama_kv_cache, llm_build_context (#12181)
|
10 mesi fa |
|
llama-memory.h
|
e298d2fbd0
kv-cache : add SWA support (#13194)
|
8 mesi fa |
|
llama-mmap.cpp
|
c54f6b7988
mmap : skip resource limit checks on AIX (#12541)
|
10 mesi fa |
|
llama-mmap.h
|
19b392d58d
llama-mmap: fix missing include (#11796)
|
11 mesi fa |
|
llama-model-loader.cpp
|
c6a2c9e741
gguf : use ggml log system (#13571)
|
8 mesi fa |
|
llama-model-loader.h
|
e0e912f49b
llama : add option to override model tensor buffers (#11397)
|
9 mesi fa |
|
llama-model-saver.cpp
|
10d2af0eaa
llama/ggml: add LLM training support (#10544)
|
8 mesi fa |
|
llama-model-saver.h
|
10d2af0eaa
llama/ggml: add LLM training support (#10544)
|
8 mesi fa |
|
llama-model.cpp
|
be0239693c
model : fix llama4 graph (#13663)
|
8 mesi fa |
|
llama-model.h
|
e298d2fbd0
kv-cache : add SWA support (#13194)
|
8 mesi fa |
|
llama-quant.cpp
|
e5c834f718
quantize : improve tensor-type pattern matching (#13033)
|
8 mesi fa |
|
llama-quant.h
|
f66f582927
llama : refactor `src/llama.cpp` (#10902)
|
1 anno fa |
|
llama-sampling.cpp
|
ffc727203a
sampling : make top_n_sigma no-op at <=0 or a single candidate (#13345)
|
8 mesi fa |
|
llama-sampling.h
|
afa8a9ec9b
llama : add `llama_vocab`, functions -> methods, naming (#11110)
|
1 anno fa |
|
llama-vocab.cpp
|
10d2af0eaa
llama/ggml: add LLM training support (#10544)
|
8 mesi fa |
|
llama-vocab.h
|
10d2af0eaa
llama/ggml: add LLM training support (#10544)
|
8 mesi fa |
|
llama.cpp
|
5364ae4ba5
llama : print hint when loading a model when no backends are loaded (#13589)
|
8 mesi fa |
|
unicode-data.cpp
|
458367a906
server : better security control for public deployments (#9776)
|
1 anno fa |
|
unicode-data.h
|
a39ab216aa
llama : reduce compile time and binary size (#9712)
|
1 anno fa |
|
unicode.cpp
|
68ff663a04
repo : update links to new url (#11886)
|
11 mesi fa |
|
unicode.h
|
08ea539df2
unicode : improve naming style (#10838)
|
1 anno fa |
Georgi Gerganov