LLM-Inference/ik_llama.cpp
1
0
Fork 0
mirror of https://github.com/ikawrakow/ik_llama.cpp.git synced 2026-08-12 22:29:39 +04:00
Code Issues Packages Projects Releases Wiki Activity
Files
61b37f5f448e6c5d4f707ddcded3c797e01159c6
ik_llama.cpp/src
T
History
Kawrakow 36925b86c1 Compiler warning
2026-08-07 06:10:32 +00:00
..
graphs
deepseek4: compacted sliding-window KV cache (--swa-compress) (#2266)
2026-08-07 08:36:08 +03:00
CMakeLists.txt
DS4: slowly approaching a meaningful performance (#2165)
2026-07-22 17:18:57 +03:00
llama-arch.cpp
DeepSeek 4 MTP implementation (#2216)
2026-08-01 16:45:48 +03:00
llama-arch.h
DeepSeek 4 MTP implementation (#2216)
2026-08-01 16:45:48 +03:00
llama-build-context.cpp
deepseek4: compacted sliding-window KV cache (--swa-compress) (#2266)
2026-08-07 08:36:08 +03:00
llama-build-context.h
deepseek4: compacted sliding-window KV cache (--swa-compress) (#2266)
2026-08-07 08:36:08 +03:00
llama-context.h
Compute the sequence fingerprint once per decode (#2265)
2026-08-06 17:34:42 +03:00
llama-cparams.h
openpangu: opt-in compacted sliding-window KV cache (--swa-compress) (#2253)
2026-08-05 18:00:32 +03:00
llama-delta-net.cpp
ggml : fuse the delta-net recurrent state copy into the op (#2251)
2026-08-04 19:27:27 +03:00
llama-delta-net.h
MTP: faster recurrent state restore (#1791)
2026-05-13 11:00:24 +03:00
llama-dflash.cpp
openpangu: opt-in compacted sliding-window KV cache (--swa-compress) (#2253)
2026-08-05 18:00:32 +03:00
llama-dflash.h
DFlash: use persistent FA-ready K/V cache (#1997)
2026-06-22 16:49:35 +02:00
llama-dsv4.cpp
deepseek4: compacted sliding-window KV cache (--swa-compress) (#2266)
2026-08-07 08:36:08 +03:00
llama-dsv4.h
DeepSeek V4 spec checkpoints (#2205)
2026-07-30 13:34:33 +03:00
llama-expert-io.h
Add --defer-experts flag to defer expert mmap residency on Linux (#1634)
2026-04-16 08:54:44 +02:00
llama-grammar.cpp
Bug fixes (#1940)
2026-06-10 07:45:49 +02:00
llama-grammar.h
llama : add token matching support to llama-grammar (#1220)
2026-02-03 07:57:17 +02:00
llama-hparams.cpp
speculative : add Step 3.7 MTP support (#2250)
2026-08-07 07:23:21 +03:00
llama-hparams.h
deepseek4: compacted sliding-window KV cache (--swa-compress) (#2266)
2026-08-07 08:36:08 +03:00
llama-impl.h
Split mode graph for dense Gemma4 assistant (#2022)
2026-06-24 18:29:32 +02:00
llama-load-tensors.cpp
Compiler warning
2026-08-07 06:10:32 +00:00
llama-mmap.cpp
Chores : tidy up more typos project wide (ggml directory excluded), new -ptcall alias (#2237)
2026-08-03 08:01:18 +03:00
llama-mmap.h
Parallelize weight loading for weights targeted at anonymous host ram and also GPU (#2057)
2026-07-07 09:52:19 +02:00
llama-model-loader.cpp
DS4: slowly approaching a meaningful performance (#2165)
2026-07-22 17:18:57 +03:00
llama-model-loader.h
Split mode graph for dense Gemma4 assistant (#2022)
2026-06-24 18:29:32 +02:00
llama-model.cpp
deepseek4: compacted sliding-window KV cache (--swa-compress) (#2266)
2026-08-07 08:36:08 +03:00
llama-model.h
deepseek4: compacted sliding-window KV cache (--swa-compress) (#2266)
2026-08-07 08:36:08 +03:00
llama-quantize.cpp
Do not quantize integer tensors (#2246)
2026-08-03 10:42:17 +03:00
llama-quantize.h
Allow using -rtr and -muge together (#1444)
2026-03-16 18:26:26 +01:00
llama-reload-info.h
on-demand tensor reload (#1989)
2026-06-22 16:36:34 +02:00
llama-reload.cpp
hotswap: keep load-time-derived and transformed tensors coherent after reloads (follow-up to #2131) (#2163)
2026-07-22 17:34:43 +03:00
llama-sampling.cpp
sampling : fix use-after-scope in grammar trigger_words path (#2221)
2026-08-01 08:55:31 +03:00
llama-sampling.h
Add adaptive sampling clone and free functions to manage memory (#1851)
2026-05-21 08:11:17 +03:00
llama-spec-features-dflash.cpp
fix: isolate DFlash cross-device IO (#2243)
2026-08-03 19:22:29 +03:00
llama-spec-features-dflash.h
DFlash: add Laguna XS 2.1 support (#2124)
2026-07-27 07:40:10 +03:00
llama-spec-features.cpp
speculative : add Step 3.7 MTP support (#2250)
2026-08-07 07:23:21 +03:00
llama-spec-features.h
move dflash for it own file
2026-06-02 10:22:13 -03:00
llama-vocab.cpp
model: add openPangu-2.0-Flash (92B-A6B) with MLA-latent cache, DSA/SWA, mHC, and multi-head MTP (#2065)
2026-07-11 12:29:20 +03:00
llama-vocab.h
Add Mellum2 architecture support (#1919)
2026-06-04 14:28:02 +02:00
llama.cpp
deepseek4: compacted sliding-window KV cache (--swa-compress) (#2266)
2026-08-07 08:36:08 +03:00
unicode-data.cpp
Merge mainline llama.cpp (#3)
2024-07-27 07:55:01 +02:00
unicode-data.h
Merge mainline llama.cpp (#3)
2024-07-27 07:55:01 +02:00
unicode-script-data.cpp
Add Unicode allowlist (#1597)
2026-04-10 18:22:57 +02:00
unicode.cpp
Gemma4 tokenizer fixes (#1603)
2026-04-09 15:33:28 +02:00
unicode.h
Add Unicode allowlist (#1597)
2026-04-10 18:22:57 +02:00