This website requires JavaScript.
e12a0128ab
build: include libmtmd in Apple XCFramework (#21935 )
2026-06-25 01:37:30 -04:00
b3ce5cedf4
quant : fix quantizing moe with mtp (#24986 )
Sigbjørn Skjæret and GitHub
2026-06-25 07:36:49 +02:00
e9fb3b3fc0
sycl : support --split-mode tensor (#24152 )
David Spruill and GitHub
2026-06-25 01:35:21 -04:00
9c10954865
sycl : fix the failed UT cases of conv_3d (#24900 )
Neo Zhang and GitHub
2026-06-25 13:27:58 +08:00
fdb2c11c70
opencl: support non-contig rows in norm (#24965 )
lhez and GitHub
2026-06-24 19:21:25 -07:00
09cedfd699
chat: harden caps check (#24973 )
Piotr Wilkin (ilintar) and GitHub
2026-06-25 02:49:22 +02:00
8be759e6f7
hexagon: MUL_MAT and MUL_MAT_ID rework : 32x32 tiled weight repack, kernel-params, cached graphs (#24954 )
Max Krasnyansky and GitHub
2026-06-24 12:14:25 -07:00
894bb27af3
mtmd: model: unlimited-ocr: converter + parity test (#24969 )
Saba Fallah and GitHub
2026-06-24 18:20:22 +02:00
fb401045cc
common: remove unused json-partial (#24968 )
Xuan-Son Nguyen and GitHub
2026-06-24 18:12:16 +02:00
51eae8cfca
vulkan: allow reducing the graph submission batches to avoid timeouts (#24872 )
Wagner Bruna and GitHub
2026-06-24 11:29:24 -03:00
1191758c5d
vulkan: fail the build when a shader fails to compile (#24450 )
liminfei-amd and GitHub
2026-06-24 17:42:03 +08:00
00139b660b
ui: loading bar below the model picker (#24931 )
Pascal and GitHub
2026-06-24 10:50:44 +02:00
ef9c13d4c2
ui: New Logo + Navigation cleanup & Mobile UI/UX improvements (#24897 )
2026-06-24 10:21:33 +02:00
88636e178f
model : Add LFM2.5-ColBERT-350M and LFM2.5-Embedding-350M (#24913 )
Tarek Dakhran and GitHub
2026-06-24 08:49:46 +02:00
ac4105d68b
vulkan: Apply bias before softmax in FA, to avoid overflow (#24909 )
Jeff Bolz and GitHub
2026-06-23 22:34:00 -05:00
be4a6a63eb
server : check draft context creation error (#24922 )
kononnable and GitHub
2026-06-23 16:56:50 +02:00
72a9269172
vulkan: support all backend tests for SQR/SQRT/SIN/COS/CLAMP/LEAKY_RELU/NORM (#24582 )
Jeff Bolz and GitHub
2026-06-23 09:48:24 -05:00
92e854ab83
vulkan: Support GET_ROWS_BACK (#24883 )
Jeff Bolz and GitHub
2026-06-23 08:39:37 -05:00
c5606364b2
vulkan: support CONV_3D (#24612 )
Jeff Bolz and GitHub
2026-06-23 08:39:20 -05:00
0eb874d374
vulkan: make mul_mm ALIGNED a spec constant (#24689 )
Jeff Bolz and GitHub
2026-06-23 07:26:17 -05:00
75ad0b23ed
server: fix remote preset handling, add test (#24938 )
Xuan-Son Nguyen and GitHub
2026-06-23 13:28:34 +02:00
c926ad0985
vulkan: link ggml-cpu when GGML_VULKAN_CHECK_RESULTS / RUN_TESTS are enabled (#24444 )
Wyatt Caldwell and GitHub
2026-06-23 03:55:46 -07:00
a3900a6694
model: Granite Speech Plus (#24818 )
2026-06-23 04:03:31 -06:00
7c908502ea
ggml-webgpu: improve MTP inference by using mat-vec path for small batches (#24811 )
Masashi Yoshimura and GitHub
2026-06-23 17:13:55 +09:00
035cd8f9a6
codeowners: add yomaytk to ggml-webgpu (#24930 )
Masashi Yoshimura and GitHub
2026-06-23 15:19:34 +09:00
73618f27a8
server: improve user message detection and create checkpoints at every user message (#24176 )
Aldehir Rojas and GitHub
2026-06-23 00:27:28 -05:00
23ee8797e1
opencl: q8_0 gemv precision improvement (#24923 )
Shawn Gu and GitHub
2026-06-22 22:25:21 -07:00
dec5ca5577
server : Add id to tool call responses api (#24882 )
Matt Thompson and GitHub
2026-06-22 14:03:12 -07:00
9c0ac887f3
ui: Prioritize favorite models in model selection (#24766 )
Mahdiou Diallo and GitHub
2026-06-22 21:00:21 +02:00
721354fbdf
server: (router) move model downloading to dedicated process (#24834 )
Xuan-Son Nguyen and GitHub
2026-06-22 18:24:04 +02:00
6ee0f65793
server: refactor/generalize input file schema (#24299 )
Xuan-Son Nguyen and GitHub
2026-06-22 16:42:47 +02:00
099b579acb
ui: model status and load progress via /models/sse feed (#24878 )
Pascal and GitHub
2026-06-22 15:55:30 +02:00
f8cc15f163
[SYCL] support bf16 on bin_bcast OP and unary OPs (#24838 )
Neo Zhang and GitHub
2026-06-22 19:09:02 +08:00
37957e8531
sampling : remove unconditional softmax+sort in top-n-sigma sampler (#22645 )
Tim Neumann and GitHub
2026-06-22 13:08:32 +02:00
d0f9d2e5ac
server: fix edit_file crash on append at end of file (line_start -1) (#24893 )
Pascal and GitHub
2026-06-22 10:55:28 +02:00
0ef6f06d55
docs/android.md: Add dependency libandroid-spawn for building in termux (#21812 )
aafsmarak and GitHub
2026-06-22 09:18:31 +05:30
52b3df0023
common/peg : implement ac parser for stricter grammar generation (#24869 )
Aldehir Rojas and GitHub
2026-06-21 16:20:58 -05:00
7c082bc417
server: fix report progress for loading spec models, add "stages" list (#24870 )
Xuan-Son Nguyen and GitHub
2026-06-21 17:36:52 +02:00
bddfd2b113
server: refactor batch construction (#24843 )
Xuan-Son Nguyen and GitHub
2026-06-21 14:16:11 +02:00
0d135df48c
mtmd: fix mtmd_get_memory_usage (#24867 )
Xuan-Son Nguyen and GitHub
2026-06-21 14:12:15 +02:00
bf533823cd
jinja : implement call statement (#24847 )
Sigbjørn Skjæret and GitHub
2026-06-21 14:04:52 +02:00
2f89acc2bc
mtmd: add load progress callback (#24865 )
Xuan-Son Nguyen and GitHub
2026-06-21 13:40:52 +02:00
bfa3219177
server: add "verbose" field to schema (#24864 )
Xuan-Son Nguyen and GitHub
2026-06-21 13:03:14 +02:00
d6d899580d
server: real-time model load progress tracking via /models/sse (#24828 )
Xuan-Son Nguyen and GitHub
2026-06-21 11:58:14 +02:00
8a118ee86c
minor : clean-up whitespaces (#24862 )
Georgi Gerganov and GitHub
2026-06-21 11:37:12 +03:00
d789527482
spec : Support Step3.5/3.7 flash mtp3 (#24340 )
2026-06-21 16:33:18 +08:00
063d9c156e
common/peg : refactor until gbnf grammar generation (#24839 )
Aldehir Rojas and GitHub
2026-06-20 21:15:06 -05:00
c57607016a
common/json-schema-to-grammar : align spacing rules with parsers (#24835 )
Aldehir Rojas and GitHub
2026-06-20 17:43:04 -05:00
4a80943174
fix(hexagon): use padded stride for ssm-conv weights (#24470 )
Guanhuai Zhang and GitHub
2026-06-21 05:58:49 +08:00
84de01a1f1
llama : use LLM_KV for quantization_version & file_type (#24802 )
Adrien Gallouët and GitHub
2026-06-20 20:07:01 +02:00
75f460ac28
arg: try fixing test-args-parser randomly fails (#24826 )
2026-06-20 19:45:27 +02:00
8452824611
release: add missing link for win opencl adreno arm64 (#24809 )
Muhammad Salem and GitHub
2026-06-20 18:08:59 +03:00
e27f308597
server: avoid forwarding auth headers in CORS proxy (#24373 )
2026-06-20 15:34:47 +02:00
67e9fd3b74
docker : prebuild web UI for s390x build [no release] (#24829 )
Aldehir Rojas and GitHub
2026-06-20 05:54:42 -05:00
796f41bedc
model : glm-dsa load DSA indexer tensors as optional (#24770 )
davidrhodus and GitHub
2026-06-20 03:48:24 -07:00
37a77fb057
ggml : optimize AMX (#24806 )
Adrien Gallouët and GitHub
2026-06-20 12:43:06 +02:00
f4043fec01
convert : more consistent handling of rope_parameters (#24833 )
Sigbjørn Skjæret and GitHub
2026-06-20 12:42:36 +02:00
f449e05537
ggml-webgpu: add adapter toggles for F16 on Vulkan + NVIDIA
Masashi Yoshimura and GitHub
2026-06-20 08:12:32 +09:00
2b686a9120
server: refactor child --> router communication (#24821 )
Xuan-Son Nguyen and GitHub
2026-06-20 01:02:26 +02:00
4b48a53b6c
server : optimize get_token_probabilities (#24796 )
Adrien Gallouët and GitHub
2026-06-19 23:26:54 +02:00
e475fa2b5f
mtmd, arg: fix utf8 handling on windows (#24779 )
Xuan-Son Nguyen and GitHub
2026-06-19 22:28:38 +02:00
175147e8f6
server: remove all internal mentions about "webui" (#24817 )
Xuan-Son Nguyen and GitHub
2026-06-19 22:12:46 +02:00
fabde3bf51
arg: Add comment line support to --api-key-file (#23168 )
Mikolaj Kucharski and GitHub
2026-06-19 15:33:54 +00:00
0d2d9ccbf6
vendor : update cpp-httplib to 0.48.0 (#24787 )
Alessandro de Oliveira Faria (A.K.A.CABELO) and GitHub
2026-06-19 11:16:35 -03:00
8c2d6f6475
server: add --agent arg, remove redundant webui naming compat (#24801 )
Xuan-Son Nguyen and GitHub
2026-06-19 16:06:13 +02:00
38724ab593
docker : build the UI (#24794 )
Aldehir Rojas and GitHub
2026-06-19 08:32:31 -05:00
e2e7a9b2d0
mtmd: several bug fixes (#24784 )
Xuan-Son Nguyen and GitHub
2026-06-19 12:18:36 +02:00
b14e3fb90c
spec: support eagle3 for qwen3.5 & 3.6 (#24593 )
2026-06-19 12:08:50 +02:00
159d093a43
server: fix non-bound n_discard value (ctx shifting) (#24786 )
2026-06-19 10:53:44 +02:00
5fd2dc2c41
sync : ggml
Georgi Gerganov
2026-06-19 10:18:14 +03:00
1868af13ac
ggml : bump version to 0.15.2 (ggml/1548)
Georgi Gerganov
2026-06-19 10:14:26 +03:00
5bd21b8555
pi : remove docs from system prompt (#24791 )
Georgi Gerganov and GitHub
2026-06-19 09:34:00 +03:00
80452d65b9
server : consolidate slot selection into get_available_slot (#24755 )
Georgi Gerganov and GitHub
2026-06-19 09:22:34 +03:00
8141e730f1
ggml-cpu: support K tails in power10 Q8/Q4 MMA matmul (#24753 )
2026-06-19 11:25:38 +05:30
db52540f73
mtmd: add batching support for internvl (#24775 )
Xuan-Son Nguyen and GitHub
2026-06-19 01:16:16 +02:00
3a3edc9ac6
Ggml/cuda col2im 1d (#24417 )
Pascal and GitHub
2026-06-18 22:23:01 +02:00
40f3aafc45
server: add "X-Accel-Buffering": "no" header to streaming endpoints (#24774 )
Reguna and GitHub
2026-06-19 04:01:24 +08:00
a6b3260a42
mtmd: add batching for mtmd-cli, add video tests (#24778 )
Xuan-Son Nguyen and GitHub
2026-06-18 21:55:04 +02:00
32eddaf2ea
cmake : fix ui build with read-only source (#24752 )
o7si and GitHub
2026-06-19 00:59:18 +08:00
060ce1bf72
mtmd: refactor llava-uhd overview image handling (always use ov_img_first) (#24769 )
Xuan-Son Nguyen and GitHub
2026-06-18 18:53:49 +02:00
d2c67959b3
hexagon: support for op-trace (fine-grain tracing of HVX/HMX/DMA events) (#24592 )
Max Krasnyansky and GitHub
2026-06-18 08:35:02 -07:00
7b6c5a2aed
docs: fix export-lora --lora-scaled syntax [no release] (#24703 )
Kangjia Gao and GitHub
2026-06-18 22:46:17 +08:00
fe7c8b2414
server: (router) fix stopping_thread potentially hang (#24728 )
Xuan-Son Nguyen and GitHub
2026-06-18 15:41:09 +02:00
e1efd0991d
server: add "schema" and validation (#24150 )
Xuan-Son Nguyen and GitHub
2026-06-18 15:40:58 +02:00
08023072ef
server : add last-5-seconds generation speed display (#24291 )
2026-06-18 15:02:20 +03:00
20832179e2
ui: provide touch accessible model selection UI (#24604 )
Amos Wong and GitHub
2026-06-18 19:14:20 +08:00
10786217e9
server : return HTTP 400 on invalid grammar (#24144 ) (#24154 )
Anuj Attri and GitHub
2026-06-18 06:49:14 -04:00
552258c535
server: (router) rework -hf preset repo (#24739 )
Xuan-Son Nguyen and GitHub
2026-06-18 12:45:23 +02:00
968c43891a
server: fix router args not being forwarded to child instances (#24760 )
Xuan-Son Nguyen and GitHub
2026-06-18 12:15:46 +02:00
24bba7b98e
mtmd: refactor preprocessor, add mtmd_image_preproc_out (#24736 )
Xuan-Son Nguyen and GitHub
2026-06-18 12:04:39 +02:00
9724f664e8
[SYCL] rename GGML_SYCL_SUPPORT_LEVEL_ZERO (#24719 )
Neo Zhang and GitHub
2026-06-18 16:18:26 +08:00
dd69db2924
sycl : support MUL_MAT and OUT_PROD with Q1_0 (#24721 )
Neo Zhang and GitHub
2026-06-18 16:17:37 +08:00
6ec59ddaea
app : enable self-update only when built with llama-install.sh (#24754 )
Adrien Gallouët and GitHub
2026-06-18 09:57:59 +02:00
32e806b9c1
ci : fix check-release message parsing (#24751 )
Sigbjørn Skjæret and GitHub
2026-06-18 09:32:56 +02:00
6f1034b32a
[SYCL] support OPs: conv_2d, conv_2d_dw, conv2d_transpose (#24600 )
Neo Zhang and GitHub
2026-06-18 14:40:03 +08:00
0b73fc79fe
ui: Update code formatting command in pre-commit hook (#24685 )
Aleksander Grygier and GitHub
2026-06-18 08:33:50 +02:00
4a79037b8b
ci : fix Windows x64 (OpenVINO) release link (#24731 )
Ravi Panchumarthy and GitHub
2026-06-17 23:30:08 -07:00
cae0a3b0b0
metal : check for BF16 support in concat kernel (#24747 )
Georgi Gerganov and GitHub
2026-06-18 09:16:06 +03:00
f3e1828164
mtmd: llava_uhd should no longer use batch dim (#24732 )
Xuan-Son Nguyen and GitHub
2026-06-17 22:40:50 +02:00
2e88c49c90
ggml-cpu: Conditionally enable power11 backend based on compiler support (#24687 )
shalinib-ibm and GitHub
2026-06-18 00:15:19 +05:30
