replica
/
llama.cpp
mirror of https://github.com/ggml-org/llama.cpp.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity
llama.cpp/src
History
Dongliang Wei 6c6e397aff
model : add support for SmallThinker series (#14898) 
* support smallthinker

* support 20b softmax, 4b no sliding window

* new build_moe_ffn_from_probs, and can run 4b

* fix 4b rope bug

* fix python type check

* remove is_moe judge

* remove set_dense_start_swa_pattern function and modify set_swa_pattern function

* trim trailing whitespace

* remove get_vocab_base of SmallThinkerModel in convert_hf_to_gguf.py

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

* better whitespace

Apply suggestions from code review

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

* use GGML_ASSERT for expert count validation

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

* Improve null pointer check for probs

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

* use template parameter for SWA attention logic

* better whitespace

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

* move the creation of inp_out_ids before the layer loop

* remove redundant judge for probs

---------

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
 		2025-07-28 13:47:00 +02:00
..
CMakeLists.txt memory : Hybrid recurrent cache (#13979) 2025-06-19 08:08:14 +03:00
llama-adapter.cpp llama : do not crash if there is no CPU backend (#13395) 2025-05-09 13:02:07 +02:00
llama-adapter.h llama : refactor llama_context, llama_kv_cache, llm_build_context (#12181) 2025-03-13 12:35:44 +02:00
llama-arch.cpp model : add support for SmallThinker series (#14898) 2025-07-28 13:47:00 +02:00
llama-arch.h model : add support for SmallThinker series (#14898) 2025-07-28 13:47:00 +02:00
llama-batch.cpp llama : reuse compute graphs (#14482) 2025-07-17 19:08:33 +03:00
llama-batch.h llama : reuse compute graphs (#14482) 2025-07-17 19:08:33 +03:00
llama-chat.cpp chat : fix kimi-k2 chat template (#14852) 2025-07-24 13:59:56 +02:00
llama-chat.h model : add EXAONE 4.0 support (#14630) 2025-07-18 10:45:49 +02:00
llama-context.cpp llama : clarify comment about pp and tg graphs [no ci] (#14895) 2025-07-27 12:10:51 +02:00
llama-context.h context : restore preemptive sched reset when LLAMA_SET_ROWS=0 (#14870) 2025-07-25 14:28:06 +03:00
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 : add high-throughput mode (#14363) 2025-07-16 16:35:42 +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 model : add support for SmallThinker series (#14898) 2025-07-28 13:47:00 +02:00
llama-graph.h model : add support for SmallThinker series (#14898) 2025-07-28 13:47:00 +02:00
llama-hparams.cpp model : add support for SmallThinker series (#14898) 2025-07-28 13:47:00 +02:00
llama-hparams.h model : add support for SmallThinker series (#14898) 2025-07-28 13:47:00 +02:00
llama-impl.cpp GGUF: C++ refactor, backend support, misc fixes (#11030) 2025-01-07 18:01:58 +01:00
llama-impl.h cleanup: fix compile warnings associated with gnu_printf (#11811) 2025-02-12 10:06:53 -04:00
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-unified-iswa.cpp llama : add high-throughput mode (#14363) 2025-07-16 16:35:42 +03:00
llama-kv-cache-unified-iswa.h llama : add high-throughput mode (#14363) 2025-07-16 16:35:42 +03:00
llama-kv-cache-unified.cpp kv-cache : fix k-shift for multiple streams (#14742) 2025-07-17 20:52:33 +03:00
llama-kv-cache-unified.h llama : reuse compute graphs (#14482) 2025-07-17 19:08:33 +03:00
llama-kv-cells.h kv-cache : use ggml_set_rows (#14285) 2025-07-03 10:53:35 +03:00
llama-memory-hybrid.cpp llama : fix parameter order for hybrid memory initialization (#14725) 2025-07-16 21:17:25 +02:00
llama-memory-hybrid.h kv-cache : use ggml_set_rows (#14285) 2025-07-03 10:53:35 +03:00
llama-memory-recurrent.cpp memory : handle saving/loading null layers in recurrent memory (#14675) 2025-07-23 11:16:41 +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 memory : correctly handle failure in apply() (#14438) 2025-06-30 18:03:03 +03:00
llama-memory.h memory : correctly handle failure in apply() (#14438) 2025-06-30 18:03:03 +03:00
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 llama : support multiple classifier outputs and labels (#13940) 2025-06-06 09:03:25 +02:00
llama-model-loader.h llama : add option to override model tensor buffers (#11397) 2025-04-02 14:52:01 +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 : add support for SmallThinker series (#14898) 2025-07-28 13:47:00 +02:00
llama-model.h model: add Ernie 4.5 MoE support (#14658) 2025-07-17 23:15:32 +02:00
llama-quant.cpp quantize : fix minor logic flaw in --tensor-type (#14572) 2025-07-13 18:02:17 +02:00
llama-quant.h llama : refactor `src/llama.cpp` (#10902) 2025-01-03 10:18:53 +02:00
llama-sampling.cpp sampling : make sure samplers return at least 1 token (#13822) 2025-05-27 12:07:52 +03:00
llama-sampling.h llama : add `llama_vocab`, functions -> methods, naming (#11110) 2025-01-12 11:32:42 +02:00
llama-vocab.cpp model : add EXAONE 4.0 support (#14630) 2025-07-18 10:45:49 +02:00
llama-vocab.h Support diffusion models: Add Dream 7B (#14644) 2025-07-16 20:03:51 +08:00
llama.cpp llama : add thread safety test (#14035) 2025-06-16 08:11:43 -07:00
unicode-data.cpp server : better security control for public deployments (#9776) 2024-10-08 13:27:04 +02:00
unicode-data.h llama : reduce compile time and binary size (#9712) 2024-10-02 15:49:55 +02:00
unicode.cpp model : add Kimi-K2 support (#14654) 2025-07-15 21:54:22 +02:00
unicode.h model : add Kimi-K2 support (#14654) 2025-07-15 21:54:22 +02:00