-
a0f3897d53
vulkan: fix top_k bug when there are ties in the input (#17659)
Jeff Bolz
2025-12-05 15:03:19 -06:00
-
e15cd06a94
vulkan : support conv-2d with large output size (#17685)
Acly
2025-12-05 21:46:39 +01:00
-
fd57b24c0f
ggml webgpu: unary op suppport, code refactoring, ops support (#17764)
Reese Levine
2025-12-05 12:25:51 -08:00
-
6ab0d64960
vulkan: enable mmvq for q2_k on NVIDIA (#17675)
Jeff Bolz
2025-12-05 14:21:57 -06:00
-
93bb92664e
vulkan: set all memory allocations to high priority (#17624)
Jeff Bolz
2025-12-05 14:21:04 -06:00
-
8160b38a5f
rpc : fix alloc size logic (#17116)
Georgi Gerganov
2025-12-05 19:39:04 +02:00
-
c41bde6fbd
metal : add residency sets keep-alive heartbeat (#17766)
Georgi Gerganov
2025-12-05 19:38:54 +02:00
-
6016d0bd41
HIP : fix RDNA4 build (#17792)
Johannes Gäßler
2025-12-05 13:47:52 +01:00
-
1be97831e4
fix: prevent segfault in tokenizer on highly repetitive input (#17786)
Pascal
2025-12-05 12:52:23 +01:00
-
a6cfc212ed
ci : fix winget workflow (#17790)
Adrien Gallouët
2025-12-05 12:44:17 +01:00
-
3a0d10533a
Q4/Q8 Tiled Gemm Optimization. (#16999)
shalinib-ibm
2025-12-05 17:11:51 +05:30
-
6648989673
Add pwilkin to CODEOWNERS for chat files (#17789)
Piotr Wilkin (ilintar)
2025-12-05 12:00:57 +01:00
-
e95d0bc8fd
CUDA: fix FA VKQ accumulator overflow (#17746)
Johannes Gäßler
2025-12-05 09:18:10 +01:00
-
668ed76574
HIP: enable WMMA-MMQ INT kernels for RDNA 3 (#17576)
Jiacheng (Jason) Chen
2025-12-05 03:17:37 -05:00
-
03d9a77b85
ci : transform release binary root dir in tar to llama-bXXXX (#17773)
Sigbjørn Skjæret
2025-12-05 01:50:19 +01:00
-
3143a755c8
docs : update ops.md (Metal, BLAS) (#17768)
Gabe Goodhart
2025-12-04 16:55:34 -07:00
-
96fe9badfc
Add support for CUMSUM and TRI for CUDA. (#17584)
Piotr Wilkin (ilintar)
2025-12-04 22:19:51 +01:00
-
bde188d60f
metal: TRI, FILL, EXPM1, SOFTPLUS (#16623)
Gabe Goodhart
2025-12-04 10:12:19 -07:00
-
9d0229967a
server: strip content-length header on proxy (#17734)
Xuan-Son Nguyen
2025-12-04 16:32:57 +01:00
-
c4c10bfb86
server: move msg diffs tracking to HTTP thread (#17740)
Xuan-Son Nguyen
2025-12-04 15:46:08 +01:00
-
817d743cc1
examples : add missing code block end marker [no ci] (#17756)
Daniel Bevenius
2025-12-04 14:17:30 +01:00
-
bd4ef13476
common : skip model validation when --help is requested (#17755)
Daniel Bevenius
2025-12-04 13:36:50 +01:00
-
87a2084c45
ggml-cpu : remove asserts always evaluating to false (#17728)
Alberto Cabrera Pérez
2025-12-04 12:16:38 +00:00
-
3659aa28e9
convert: use existing local chat_template if mistral-format model has one. (#17749)
SmartestWashingMachine
2025-12-04 22:12:45 +11:00
-
2a73f81f8a
cmake : simplify build info detection using standard variables (#17423)
Adrien Gallouët
2025-12-04 11:42:13 +01:00
-
7dba049b07
ci : disable ggml-ci-x64-amd-* (#17753)
Sigbjørn Skjæret
2025-12-04 11:25:08 +01:00
-
83c1171529
common: use native MultiByteToWideChar (#17738)
Adrien Gallouët
2025-12-04 11:06:49 +01:00
-
0d1324856f
metal : use params per pipeline instance (#17739)
Georgi Gerganov
2025-12-04 10:34:11 +02:00
-
a67ef0f47f
llama : fix sanity checks during quantization (#17721)
Georgi Gerganov
2025-12-04 10:33:42 +02:00
-
ef75a89fdb
build : move _WIN32_WINNT definition to headers (#17736)
Adrien Gallouët
2025-12-04 07:04:02 +01:00
-
d8b5cdc4fe
build: enable parallel builds in msbuild using MTT (#17708)
Jeff Bolz
2025-12-03 22:42:29 -06:00
-
dea9ba27cb
ggml-cpu: remove duplicate conditional check 'iid' (#17650)
Herman Semenoff
2025-12-04 00:03:19 +03:00
-
c6d1a00aa7
Add a couple of file types to the text section (#17670)
Piotr Wilkin (ilintar)
2025-12-03 21:45:06 +01:00
-
424c579455
convert : support latest mistral-common (fix conversion with --mistral-format) (#17712)
SmartestWashingMachine
2025-12-04 07:15:04 +11:00
-
e9f9483464
Use OpenAI-compatible
/v1/models endpoint by default (#17689)
Aleksander Grygier
2025-12-03 20:49:09 +01:00
-
41c5e02f42
webui: Fix zero pasteLongTextToFileLen to disable conversion being overridden (#17445)
Andika Wasisto
2025-12-04 02:45:17 +07:00
-
2e1c9cd814
CUDA: generalized (mma) FA, add Volta support (#17505)
Johannes Gäßler
2025-12-03 16:57:05 +01:00
-
190c4838bd
chat : reserve memory in compute_diffs and improve naming (#17729)
Georgi Gerganov
2025-12-03 17:22:10 +02:00
-
e7c2cf1356
server: add router multi-model tests (#17704) (#17722)
Pascal
2025-12-03 15:10:37 +01:00
-
1257491047
server : fix bad fmt, size() is a size_type (#17735)
Adrien Gallouët
2025-12-03 14:47:22 +01:00
-
083e18b11c
cmake: explicitly link against crypt32 on non-MSVC Windows builds (#17727)
Adrien Gallouët
2025-12-03 14:47:02 +01:00
-
3d94e967a1
metal : fix data race in pipeline library (#17731)
Georgi Gerganov
2025-12-03 14:03:40 +02:00
-
7feb0a1005
ci : remove the build of openeuler-cann in release (#17724)
jiahao su
2025-12-03 19:24:59 +08:00
-
0a8026e768
common : introduce composable PEG parser combinators for chat parsing (#17136)
Aldehir Rojas
2025-12-03 04:45:32 -06:00
-
5ceed62421
server: fix duplicate HTTP headers in multiple models mode (#17698)
Pascal
2025-12-03 10:28:43 +01:00
-
7ca5991d2b
ggml webgpu: add support for emscripten builds (#17184)
Reese Levine
2025-12-03 01:25:34 -08:00
-
b3e3060f4e
ci : move release details to the top visible by default (#17719)
Sigbjørn Skjæret
2025-12-03 09:22:46 +01:00
-
37adc9c6ba
ggml, llama : use defaulted constructors/destructors (#17649)
Herman Semenoff
2025-12-03 09:12:18 +03:00
-
16cc3c606e
build: document how to compile with Vulkan using Debian/Ubuntu packages (#17688)
Marcos Del Sol Vives
2025-12-03 01:25:11 +01:00
-
13628d8bdb
server: add --media-path for local media files (#17697)
Xuan-Son Nguyen
2025-12-02 22:49:20 +01:00
-
a96283adc4
mtmd: fix --no-warmup (#17695)
Xuan-Son Nguyen
2025-12-02 22:48:08 +01:00
-
4eba8d9451
ci : RVV1.0 builds with tests (#16682)
Ali Tariq
2025-12-03 01:46:10 +05:00
-
61bde8e21f
vulkan: Reduce temporary memory usage for TOP_K (#17623)
Jeff Bolz
2025-12-02 12:22:04 -06:00
-
e251e5ebbe
cmake : add utf8 compilation options for msvc (#17682)
xiaobing318
2025-12-03 01:50:57 +08:00
-
c4357dcc35
Server: Change Invalid Schema from Server Error (500) to User Error (400) (#17572)
Chad Voegele
2025-12-02 10:33:50 -06:00
-
e148380c7c
ggml : use svcntb() for SVE vector length detection (#17474)
Adrien Gallouët
2025-12-02 17:21:11 +01:00
-
a2b0fe8d37
CANN: Disable Ger operator of OUT_PROD on 310p device (#17563)
TianHao324
2025-12-02 20:35:23 +08:00
-
7f3a72a8ed
ggml : remove redundant n_copies check when setting input/output (#17612)
Daniel Bevenius
2025-12-02 12:52:45 +01:00
-
b9a37717b0
codeowners : remove ericcurtin (#17658)
Eric Curtin
2025-12-02 11:18:15 +00:00
-
f3a9674ae8
llama : fix signed comparison warning on FreeBSD (#17497)
Adrien Gallouët
2025-12-02 12:05:38 +01:00
-
2c453c6c77
convert: add error message for mistral3 quantized weight (#17686)
Xuan-Son Nguyen
2025-12-02 11:48:31 +01:00
-
5d6bd842ea
server: remove default "gpt-3.5-turbo" model name (#17668)
Xuan-Son Nguyen
2025-12-02 11:38:57 +01:00
-
fd3abe849e
server: fixing naming conflict res_error in server-models.cpp (#17679)
senhtry
2025-12-02 18:18:39 +08:00
-
682e6658bb
server: explicitly set exec path when create new instance (#17669)
Xuan-Son Nguyen
2025-12-02 10:25:11 +01:00
-
4574f2949e
ci : skip winget update when not in ggml-org (#17465)
Adrien Gallouët
2025-12-02 10:15:01 +01:00
-
ab6726eeff
ggml : add fallback definition for HWCAP2_SVE2 (#17683)
Adrien Gallouët
2025-12-02 09:41:26 +01:00
-
cee92af553
Add context info to server error (#17663)
Aleksander Grygier
2025-12-02 09:20:57 +01:00
-
ed32089927
ggml-cuda: reorder only relevant nodes (#17639)
Aman Gupta
2025-12-02 12:36:31 +08:00
-
7b6d745364
release: fix duplicate libs, store symbolic links (#17299)
Aaron Teo
2025-12-02 11:52:05 +08:00
-
98bd9ab1e4
enhance argsort for UT (#17573)
Neo Zhang Jianyu
2025-12-02 08:56:46 +08:00
-
746f9ee889
Override SSM_A op for Qwen3 Next to reduce splits (#17587)
Piotr Wilkin (ilintar)
2025-12-02 00:43:13 +01:00
-
9810cb8247
ops.md: update vulkan support (#17661)
Jeff Bolz
2025-12-01 15:26:21 -06:00
-
ecf74a8417
mtmd: add mtmd_context_params::warmup option (#17652)
Xuan-Son Nguyen
2025-12-01 21:32:25 +01:00
-
00c361fe53
fix: llama arch implementation (#17665)
Gilad S.
2025-12-01 22:21:13 +02:00
-
ec18edfcba
server: introduce API for serving / loading / unloading multiple models (#17470)
Xuan-Son Nguyen
2025-12-01 19:41:04 +01:00
-
7733409734
common: improve verbosity level definitions (#17630)
Xuan-Son Nguyen
2025-12-01 14:38:13 +01:00
-
cd3c118908
model: support Ministral3 (#17644)
Xuan-Son Nguyen
2025-12-01 12:26:52 +01:00
-
649495c9d9
metal : add FA head size 48 (#17619)
Georgi Gerganov
2025-12-01 12:49:53 +02:00
-
90c72a614a
ggml : extend the GGML_SCHED_NO_REALLOC debug logic of the scheduler (#17617)
Georgi Gerganov
2025-12-01 12:49:33 +02:00
-
6eea666912
llama-graph: avoid expand_forward for fusion (#17633)
Aman Gupta
2025-12-01 17:12:48 +08:00
-
ff90508d68
contributing: update guidelines for AI-generated code (#17625)
Xuan-Son Nguyen
2025-11-30 22:51:34 +01:00
-
0a4aeb927d
cmake : add option to build and link LibreSSL (#17552)
Adrien Gallouët
2025-11-30 22:14:32 +01:00
-
2ba719519d
model: LFM2-VL fixes (#17577)
Tarek Dakhran
2025-11-30 21:57:31 +01:00
-
7f8ef50cce
clip: fix nb calculation for qwen3-vl (#17594)
Xuan-Son Nguyen
2025-11-30 15:33:55 +01:00
-
3c136b21a3
cli: add migration warning (#17620)
Xuan-Son Nguyen
2025-11-30 15:32:43 +01:00
-
beb1f0c503
common : throttle download progress output to reduce IO flush (#17427)
Adrien Gallouët
2025-11-30 13:22:44 +01:00
-
def5404f26
common: add LLAMA_LOG_FILE env var (#17609)
Aaron Teo
2025-11-30 19:12:32 +08:00
-
fa0465954f
ggml: fix: macOS build with
-DGGML_BACKEND_DL=ON (#17581)
Gilad S.
2025-11-30 04:00:59 +02:00
-
5a6241feb0
common: update env var name (#17588)
ddh0
2025-11-29 19:59:25 -06:00
-
c7af376c29
CUDA: add stream-based concurrency (#16991)
Aman Gupta
2025-11-30 08:17:55 +08:00
-
00425e2ed1
cuda : add error checking for cudaMemcpyAsync in argsort (#17599)
Mahekk Shaikh
2025-11-29 19:16:28 -05:00
-
385c3da5e6
vulkan : fix FA mask load with bounds check (coopmat2) (#17606)
Acly
2025-11-30 01:03:21 +01:00
-
ab49f094d2
server: move server-context to its own cpp|h (#17595)
Xuan-Son Nguyen
2025-11-29 22:04:44 +01:00
-
8c32d9d96d
server: explicitly set the function name in lambda (#17538)
Haiyue Wang
2025-11-30 01:43:29 +08:00
-
0874693b44
common : fix json schema with '\' in literals (#17307)
Igor Smirnov
2025-11-29 21:06:32 +05:00
-
7d2add51d8
sycl : support to malloc memory on device more than 4GB, update the doc and script (#17566)
Neo Zhang
2025-11-29 20:59:44 +08:00
-
f698a79c63
ggml: replace hwcap with riscv_hwprobe for RVV detection (#17567)
ixgbe
2025-11-29 20:56:31 +08:00
-
47a268ea50
Vulkan: MMVQ Integer Dot K-Quant and MUL_MAT_ID support (#16900)
Ruben Ortlam
2025-11-29 09:37:22 +01:00
-
59d8d4e963
vulkan: improve topk perf for large k, fix overflow in unit tests (#17582)
Jeff Bolz
2025-11-29 01:39:57 -06:00
-
d82b7a7c1d
gguf-py : fix passing non-native endian tensors (editor-gui and new-metadata) (#17553)
Aleksei Nikiforov
2025-11-28 20:53:01 +01:00