leejet
d07d48d466
refactor: separate CPU kernels from shared operator extensions
2026-11-01 00:44:28 +08:00
leejet
d11410eee7
refactor: share CUDA-style extension kernels across backends
2026-11-01 00:21:35 +08:00
leejet
7ab323ef25
refactor: move Vulkan RoPE kernels into extensions
2026-10-31 23:39:19 +08:00
leejet
5c5535d01d
refactor: register CUDA affine fusion extensions
2026-10-31 22:59:06 +08:00
leejet
7ad74e6490
refactor: register CUDA INT8 GEMM and epilogue extensions
2026-10-31 22:29:12 +08:00
leejet
ba2188624e
refactor: move CUDA ConvRot fusion into extensions
2026-10-31 21:18:40 +08:00
leejet
773b11caa7
refactor: move CUDA INT8 residual fusion into extensions
2026-10-31 20:55:44 +08:00
leejet
b71db9a314
feat: add CUDA execution for custom INT8 operators
2026-10-31 20:24:30 +08:00
leejet
ab232a474b
refactor: register INT8 projection and attention fusion
2026-10-31 20:01:41 +08:00
leejet
1d2d31ffb6
refactor: register CUDA RoPE kernels and fusion in sd.cpp
2026-10-31 19:18:40 +08:00
leejet
4b274821e9
refactor: register CuTe attention and fusion in sd.cpp
2026-10-31 19:00:24 +08:00
Wagner Bruna
20050815ac
chore: clean up include paths ( #2175 )
2026-10-20 22:58:52 +08:00
leejet
d763dae3b8
feat: add per-module automatic flash attention selection ( #2132 )
2026-10-13 22:58:45 +08:00
leejet
1330cebae8
feat: support building with upstream ggml ( #1999 )
2026-09-19 22:25:01 +08:00
leejet
17860c0e45
perf: parallelize host tensor elementwise and broadcast ops ( #1998 )
2026-09-19 21:46:16 +08:00
leejet
9982c9caae
fix: propagate CUDA driver dependency to shared library consumers
2026-09-19 18:04:59 +08:00
leejet
adcac69650
perf: pad small attention heads to 64 for MMA Flash Attention ( #1992 )
2026-09-18 23:59:58 +08:00
leejet
4964abdfc5
feat: support external Hugging Face tokenizer JSON files ( #1973 )
2026-09-15 00:27:39 +08:00
leejet
9a977388a8
fix: guard GPU memory capacity and propagate encoding failures ( #1958 )
2026-09-13 21:35:46 +08:00
leejet
14eddb32b1
refactor: split generation pipeline out of stable-diffusion.cpp ( #1957 )
2026-09-11 00:57:14 +08:00
assouan and leejet
6c57cc3b38
feat: prefetch streamed layers during compute ( #1905 )
...
Co-authored-by: leejet <leejet714@gmail.com >
2026-09-06 16:35:30 +08:00
Huang, Hong-Chang
b4e67d1221
fix(cmake): only apply /MP to the MSVC compiler, not icx ( #1846 )
2026-08-04 22:37:30 +08:00
fszontagh
c00a9e956d
feat: AnimateDiff SD 1.5 motion modules (v2 + v3) ( #1784 )
2026-07-14 23:58:03 +08:00
Cyberhan123 and leejet
c1790754d3
feat: enhanced third-party integrations ( #1632 )
...
* feat: add installation support and configuration files for stable-diffusion
* fix: correct public header setting and update version variable in pkg-config
* fix stable-diffusion install package metadata
---------
Co-authored-by: leejet <leejet714@gmail.com >
2026-06-29 00:48:57 +08:00
stduhpf
c2df4e1228
feat: add RPC support ( #1629 )
2026-06-14 17:30:23 +08:00
leejet
2a07540c2a
refactor: move photomaker into generation extension ( #1618 )
2026-06-07 22:40:02 +08:00
Wagner Bruna
81abfb2548
chore: rename and reformat gits_noise.inl ( #1617 )
2026-06-07 22:30:20 +08:00
leejet
f3fd359b58
refactor: reorganize src model layout ( #1615 )
2026-06-07 03:21:12 +08:00
RapidMark
7948df8ac1
fix(cmake): build HIP backend with PIC so the static-lib PIE link succeeds ( #1593 )
2026-06-02 00:07:48 +08:00
leejet
72e512a0cc
fix: make macOS binaries use relocatable rpaths ( #1552 )
2026-05-23 12:27:06 +08:00
leejet
67dda3f897
feat: add ltx2.3 support ( #1463 )
...
* add GemmaTokenizer
* add basic ltx2.3 support
* change vocab file encoding
* fix ci
* fix ubuntu build
* add temporal tiling support
* add ltx audio support
* update ggml submodule url
* fix generate_video
* add i2v support
* minify bundled Gemma tokenizer vocab sources
* pass video fps into temporal rope embeddings
* fix av_ca_timestep_scale_multiplier
* add LTX2Scheduler support
* update docs
* fix ci
2026-05-17 16:46:20 +08:00
cphlipot
db08b84607
fix: Fix broken GCC 16 build (enforce C11/C++17 compile ) ( #1478 )
2026-05-16 16:10:16 +08:00
Craig Andrews
eeac950b44
fix: Use PkgConfig for WebP and WebM ( #1400 )
2026-05-15 00:31:10 +08:00
b8079e253d
feat: transition from compile-time to runtime backend discovery ( #1448 )
...
Co-authored-by: Stéphane du Hamel <stephduh@live.fr >
Co-authored-by: Cyberhan123 <255542417@qq.com >
Co-authored-by: leejet <leejet714@gmail.com >
2026-04-29 23:26:57 +08:00
leejet
66143340b6
refactor: move model file IO into dedicated module ( #1442 )
2026-04-19 17:52:56 +08:00
leejet
7d33d4b2dd
chore: enable MSVC parallel compilation with /MP ( #1438 )
2026-04-18 15:44:43 +08:00
leejet
9ac7b672c2
refactor: introduce shared tokenizer abstraction and split implementations ( #1423 )
2026-04-15 22:44:39 +08:00
leejet
7397ddaa86
feat: add webm support ( #1391 )
2026-04-06 01:49:28 +08:00
Wagner Bruna and leejet
687a81f251
chore: make libwebp optional and support system libwebp ( #1387 )
...
Co-authored-by: leejet <leejet714@gmail.com >
2026-04-05 23:52:05 +08:00
leejet
87ecb95cbc
feat: add webp support ( #1384 )
2026-04-02 01:36:11 +08:00
Wagner Bruna
f6968bc589
chore: remove SD_FAST_SOFTMAX build flag ( #1338 )
2026-03-15 16:42:47 +08:00
leejet
636d3cb6ff
refactor: reorganize the vocab file structure ( #1271 )
2026-02-11 00:44:17 +08:00
leejet
28ef93c0e1
refactor: reorganize the file structure ( #1266 )
2026-02-10 23:13:35 +08:00
leejet
b90b1ee9cf
chore: eliminate compilation warnings under MSVC ( #1170 )
2026-01-04 22:26:57 +08:00
Wagner Bruna
e72aea796e
feat: embed version string and git commit hash ( #1008 )
2025-12-09 22:38:54 +08:00
cmdr2
a7d6d296c7
chore: allow building ggml as a separate shared lib ( #468 )
2025-10-15 22:10:26 +08:00
clibdev
6bbaf161ad
chore: add install() support in CMakeLists.txt ( #540 )
2025-09-11 22:24:16 +08:00
leejet
675208dcb6
chore: update to c++17
2025-09-07 12:04:17 +08:00
Wagner Bruna
f7f05fb185
chore: avoid setting GGML_MAX_NAME when building against external ggml ( #751 )
...
An external ggml will most likely have been built with the default
GGML_MAX_NAME value (64), which would be inconsistent with the value
set by our build (128). That would be an ODR violation, and it could
easily cause memory corruption issues due to the different
sizeof(struct ggml_tensor) values.
For now, when linking against an external ggml, we demand it has been
patched with a bigger GGML_MAX_NAME, since we can't check against a
value defined only at build time.
2025-08-03 01:24:40 +08:00
Seas0
6167e2927a
feat: support build against system installed GGML library ( #749 )
2025-08-02 11:03:18 +08:00
leejet