nikola/llama_cpp
1
0
Fork 0
Code Issues Pull Requests Actions 4 Packages Projects Releases Wiki Activity
Files
f696428ce8e4d16c17acbffeaa7feac3b0fb9061
llama_cpp/src
History
Sigbjørn Skjæret f696428ce8 graph : add clamping to ffn_moe_weights_sum to avoid div-by-zero (#16655) 
* add missing norm topk bias

* use clamping instead, update number and add comment
2025-10-26 17:20:32 +01:00
..
CMakeLists.txt
kv-cache : drop the "unified" prefix (#15467)
2025-08-21 17:00:33 +03:00
llama-adapter.cpp
aLoRA Support (#15327)
2025-09-05 17:32:39 -06:00
llama-adapter.h
aLoRA Support (#15327)
2025-09-05 17:32:39 -06:00
llama-arch.cpp
model : add BailingMoeV2 support (#16063)
2025-10-20 21:38:20 +02:00
llama-arch.h
model : add BailingMoeV2 support (#16063)
2025-10-20 21:38:20 +02:00
llama-batch.cpp
perplexity : provide a helpful hint for has_cpl case in split_equal error. (#15304)
2025-08-14 14:03:30 +03:00
llama-batch.h
llama-batch: fix build fails with -Werror=missing-braces (#16614)
2025-10-20 11:27:09 +03:00
llama-chat.cpp
model : add BailingMoeV2 support (#16063)
2025-10-20 21:38:20 +02:00
llama-chat.h
model : add BailingMoeV2 support (#16063)
2025-10-20 21:38:20 +02:00
llama-context.cpp
llama-context: only warn on pooling_type when user specified (#16674)
2025-10-20 10:44:21 +03:00
llama-context.h
llama: print memory breakdown on exit (#15860)
2025-09-24 16:53:48 +02:00
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
llama : bump max seq limit from 64 to 256 (#15916)
2025-09-18 12:47:56 +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
tool-call: fix Qwen 2.5 Coder support, add micro benchmarks, support trigger patterns for lazy grammars (#12034)
2025-03-05 13:05:13 +00:00
llama-graph.cpp
graph : add clamping to ffn_moe_weights_sum to avoid div-by-zero (#16655)
2025-10-26 17:20:32 +01:00
llama-graph.h
graph : support cacheless embeddings with FA and iSWA (#16528)
2025-10-13 22:42:37 +03:00
llama-hparams.cpp
hparams : add check for layer index in is_recurrent (#16511)
2025-10-12 07:19:06 +02:00
llama-hparams.h
model : add BailingMoeV2 support (#16063)
2025-10-20 21:38:20 +02:00
llama-impl.cpp
…
llama-impl.h
llama: use FA + max. GPU layers by default (#15434)
2025-08-30 16:32:10 +02:00
llama-io.cpp
llama : refactor llama_context, llama_kv_cache, llm_build_context (#12181)
2025-03-13 12:35:44 +02:00
llama-io.h
llama : refactor llama_context, llama_kv_cache, llm_build_context (#12181)
2025-03-13 12:35:44 +02:00
llama-kv-cache-iswa.cpp
server : context checkpointing for hybrid and recurrent models (#16382)
2025-10-03 21:34:51 +03:00
llama-kv-cache-iswa.h
llama: print memory breakdown on exit (#15860)
2025-09-24 16:53:48 +02:00
llama-kv-cache.cpp
server : host-memory prompt caching (#16391)
2025-10-09 18:54:51 +03:00
llama-kv-cache.h
llama: print memory breakdown on exit (#15860)
2025-09-24 16:53:48 +02:00
llama-kv-cells.h
llama : remove KV cache defragmentation logic (#15473)
2025-08-22 12:22:13 +03:00
llama-memory-hybrid.cpp
memory : use sequential equal splits for recurrent modules (#16442)
2025-10-07 08:24:17 +03:00
llama-memory-hybrid.h
llama: print memory breakdown on exit (#15860)
2025-09-24 16:53:48 +02:00
llama-memory-recurrent.cpp
server : improve context checkpoint logic (#16440)
2025-10-08 10:57:29 +03:00
llama-memory-recurrent.h
llama: print memory breakdown on exit (#15860)
2025-09-24 16:53:48 +02:00
llama-memory.cpp
memory : correctly handle failure in apply() (#14438)
2025-06-30 18:03:03 +03:00
llama-memory.h
llama: print memory breakdown on exit (#15860)
2025-09-24 16:53:48 +02:00
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-mmap: fix missing include (#11796)
2025-02-10 20:58:18 +02:00
llama-model-loader.cpp
model : Apertus model implementation (#15852)
2025-10-02 20:43:22 +03:00
llama-model-loader.h
model: support GLM 4.5 family of models (#14939)
2025-08-04 20:29:25 +02:00
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 : set res->t_embd in SmallThinker models (#16782)
2025-10-26 16:08:52 +01:00
llama-model.h
model : add BailingMoeV2 support (#16063)
2025-10-20 21:38:20 +02:00
llama-quant.cpp
llama-quant: add support for mmproj (#16592)
2025-10-15 14:48:08 +02:00
llama-quant.h
…
llama-sampling.cpp
vocab : mark EOT token for Granite models (#16499)
2025-10-10 17:17:31 +03:00
llama-sampling.h
…
llama-vocab.cpp
model : add BailingMoeV2 support (#16063)
2025-10-20 21:38:20 +02:00
llama-vocab.h
model : Granite docling + Idefics3 preprocessing (SmolVLM) (#16206)
2025-10-05 14:57:47 +02:00
llama.cpp
llama-quant: add support for mmproj (#16592)
2025-10-15 14:48:08 +02:00
unicode-data.cpp
…
unicode-data.h
…
unicode.cpp
model : add Kimi-K2 support (#14654)
2025-07-15 21:54:22 +02:00
unicode.h
devops: add s390x & ppc64le CI (#15925)
2025-09-27 02:03:33 +08:00