Georgi Gerganov e92d53b29e sampling : optimize samplers by reusing bucket sort (#15665) ... * sampling : optimize sorting using bucket sort in more places ggml-ci * sampling : do not sort in dist sampler ggml-ci * sampling : avoid heap allocations for sort buffers ggml-ci * common : add option to sort sampling candidates by probability ggml-ci * sampling : revert the change for preserving sort buffers * sampling : use std::copy instead of memcpy * sampling : clarify purpose of partial sort helpers ggml-ci * cont : remove wrong comment [no ci] * common : update comment Co-authored-by: Johannes Gäßler <johannesg@5d6.de> --------- Co-authored-by: Johannes Gäßler <johannesg@5d6.de>		2025-08-31 20:41:02 +03:00
..
CMakeLists.txt	kv-cache : drop the "unified" prefix (#15467)	2025-08-21 17:00:33 +03:00
llama-adapter.cpp	model : jina-embeddings-v3 support (#13693)	2025-08-28 15:49:50 +02:00
llama-adapter.h	model : jina-embeddings-v3 support (#13693)	2025-08-28 15:49:50 +02:00
llama-arch.cpp	nvidia nemotron nano v2 (nemotronh) (#15507)	2025-08-28 18:39:31 -06:00
llama-arch.h	nvidia nemotron nano v2 (nemotronh) (#15507)	2025-08-28 18:39:31 -06:00
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-chat.cpp	model : add support for Seed-OSS (#15490)	2025-08-23 15:21:52 +02:00
llama-chat.h	model : add support for Seed-OSS (#15490)	2025-08-23 15:21:52 +02:00
llama-context.cpp	llama : fix fattn reserve call n_seqs parameter (#15699)	2025-08-31 18:47:05 +03:00
llama-context.h	llama : separate compute buffer reserve from fattn check (#15696)	2025-08-31 15:49:03 +02:00
llama-cparams.cpp
llama-cparams.h	llama : remove KV cache defragmentation logic (#15473)	2025-08-22 12:22:13 +03:00
llama-grammar.cpp
llama-grammar.h
llama-graph.cpp	llama: use FA + max. GPU layers by default (#15434)	2025-08-30 16:32:10 +02:00
llama-graph.h	llama: use FA + max. GPU layers by default (#15434)	2025-08-30 16:32:10 +02:00
llama-hparams.cpp	kv-cache : support layer reuse (#15504)	2025-08-24 13:07:07 +03:00
llama-hparams.h	kv-cache : support layer reuse (#15504)	2025-08-24 13:07:07 +03:00
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-io.h
llama-kv-cache-iswa.cpp	kv-cache : support layer reuse (#15504)	2025-08-24 13:07:07 +03:00
llama-kv-cache-iswa.h	kv-cache : support layer reuse (#15504)	2025-08-24 13:07:07 +03:00
llama-kv-cache.cpp	kv-cache : fix find_slot to not search for continuous slot (#15638)	2025-08-28 17:09:05 +03:00
llama-kv-cache.h	kv-cache : remove LLAMA_SET_ROWS checks (#15505)	2025-08-28 12:27:02 +03:00
llama-kv-cells.h	llama : remove KV cache defragmentation logic (#15473)	2025-08-22 12:22:13 +03:00
llama-memory-hybrid.cpp	kv-cache : support layer reuse (#15504)	2025-08-24 13:07:07 +03:00
llama-memory-hybrid.h	kv-cache : support layer reuse (#15504)	2025-08-24 13:07:07 +03:00
llama-memory-recurrent.cpp	kv-cache : support layer reuse (#15504)	2025-08-24 13:07:07 +03:00
llama-memory-recurrent.h	kv-cache : support layer reuse (#15504)	2025-08-24 13:07:07 +03:00
llama-memory.cpp
llama-memory.h	kv-cache : support layer reuse (#15504)	2025-08-24 13:07:07 +03:00
llama-mmap.cpp
llama-mmap.h
llama-model-loader.cpp	nvidia nemotron nano v2 (nemotronh) (#15507)	2025-08-28 18:39:31 -06:00
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-model-saver.h
llama-model.cpp	llama: use FA + max. GPU layers by default (#15434)	2025-08-30 16:32:10 +02:00
llama-model.h	model : jina-embeddings-v3 support (#13693)	2025-08-28 15:49:50 +02:00
llama-quant.cpp	convert : support non-mxfp4 HF model (#15153)	2025-08-07 23:26:03 +02:00
llama-quant.h
llama-sampling.cpp	sampling : optimize samplers by reusing bucket sort (#15665)	2025-08-31 20:41:02 +03:00
llama-sampling.h
llama-vocab.cpp	model : jina-embeddings-v3 support (#13693)	2025-08-28 15:49:50 +02:00
llama-vocab.h	model : add hunyuan dense (#14878)	2025-08-01 15:31:12 +02:00
llama.cpp	llama: use FA + max. GPU layers by default (#15434)	2025-08-30 16:32:10 +02:00
unicode-data.cpp
unicode-data.h
unicode.cpp
unicode.h