Public/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-09-19 17:24:57 +02:00
Code Issues Packages Projects Releases Wiki Activity

Commit Graph

  • d7fa69b7de ci : run ccache-clear as the last step of release jobs (#27503) b10567 Georgi Gerganov 2026-08-21 18:56:04 +03:00
  • 7cf1e7f5f5 ui : add sampling & penalties submenu to model selector allozaur/feat/model-selector-sampling-penalties-submenus Aleksander Grygier 2026-08-21 10:49:23 +02:00
  • 4fa82dc623 ui : use merged sampling & penalties section in model selector Aleksander Grygier 2026-08-21 10:49:08 +02:00
  • 9c476f0112 ui : fix eslint issues in model selector settings submenu Aleksander Grygier 2026-08-17 11:04:19 +02:00
  • 5a17ef4cc2 ui : fix formatting in model selector settings submenu Aleksander Grygier 2026-08-17 11:00:21 +02:00
  • a5e63c3069 ui : add sampling and penalties submenus to model selector Aleksander Grygier 2026-08-16 18:16:48 +02:00
  • 90a84847f6 ui : fix eslint issues in chat form and model selector Aleksander Grygier 2026-08-17 11:04:02 +02:00
  • 10ac600337 ui : fix formatting in chat form and model selector Aleksander Grygier 2026-08-17 10:59:55 +02:00
  • eedf494f04 feat: Enable microphone input as default for audio models Aleksander Grygier 2026-08-16 18:03:52 +02:00
  • 535e737a87 ui : add raw model id tooltip to model selector options Aleksander Grygier 2026-08-15 23:26:25 +02:00
  • 11294657fc ui : make model option hover and focus highlight override the active state Aleksander Grygier 2026-08-15 22:54:05 +02:00
  • f46e6cce9c ui : move model list into a submenu within the model selector Aleksander Grygier 2026-08-15 22:53:56 +02:00
  • be7321a4cc ui : add show-org-name-in-trigger display setting Aleksander Grygier 2026-08-15 22:53:48 +02:00
  • f11a90d113 ui : keep reasoning submenu visible regardless of model state Aleksander Grygier 2026-08-15 22:53:26 +02:00
  • a43c1c0cde ui : show reasoning and modality icons on model options and search by modality Aleksander Grygier 2026-08-15 22:53:18 +02:00
  • 06f8d7ae96 ui : strip trailing container-format segments from parsed model names Aleksander Grygier 2026-08-15 22:53:04 +02:00
  • 0806ae2bf0 chat : account for the tab bar offset in the assistant min-height Aleksander Grygier 2026-08-21 15:14:52 +02:00
  • b1667513bd chat : adjust tab bar width and use a shared offset variable Aleksander Grygier 2026-08-21 15:14:44 +02:00
  • 903841b24e chat : make the whole tab item act as a link Aleksander Grygier 2026-08-21 15:14:20 +02:00
  • e13011bbbd chat : add keyboard shortcut to jump between conversation tabs Aleksander Grygier 2026-08-21 15:14:08 +02:00
  • bbd11affe9 refactor: Naming Aleksander Grygier 2026-08-21 09:09:58 +02:00
  • e6d1b63385 ui : improve chat tabs carousel UX Aleksander Grygier 2026-08-21 08:46:53 +02:00
  • 3d4fa69038 ui : migrate carousels to ScrollCarousel Aleksander Grygier 2026-08-21 08:46:38 +02:00
  • 0d574e77c0 ui : add unified ScrollCarousel component Aleksander Grygier 2026-08-21 08:46:30 +02:00
  • 2e875fa3d5 ui : fix carousel scrollability detection Aleksander Grygier 2026-08-21 08:46:22 +02:00
  • 9bde74c881 refactor: Componentize Aleksander Grygier 2026-08-20 19:35:17 +02:00
  • c5fd4f9f95 feat: Add stop button to tabs Aleksander Grygier 2026-08-20 19:33:12 +02:00
  • e36d711267 chat : soften tab bar fade and dim inactive tabs Aleksander Grygier 2026-08-20 19:14:48 +02:00
  • 79434c514b chat : add close-tab keyboard shortcut Aleksander Grygier 2026-08-20 19:14:40 +02:00
  • 1723443567 chat : restyle the scroll-to-bottom button to match tab styling Aleksander Grygier 2026-08-20 18:14:00 +02:00
  • 8bcd025902 chat : turn tab bar into a horizontally scrollable carousel Aleksander Grygier 2026-08-20 18:13:52 +02:00
  • 1144652072 chat : add browser-style conversation tabs with a new-chat screen Aleksander Grygier 2026-08-20 18:13:44 +02:00
  • f8386b0368 chat : add opt-in conversation tabs setting Aleksander Grygier 2026-08-20 18:13:12 +02:00
  • b59d8bfe9d ui : track sidebar expanded state in a shared ui store Aleksander Grygier 2026-08-20 18:13:03 +02:00
  • 1ae4576fe3 ui : route new-chat entry points through tabs Aleksander Grygier 2026-08-17 14:01:40 +02:00
  • d37f8a5c4d ui : render conversation tab bar in chat layout Aleksander Grygier 2026-08-17 14:01:31 +02:00
  • 25f7bafa24 ui : add temporary new-chat tabs Aleksander Grygier 2026-08-17 14:01:22 +02:00
  • 0bc2d8d0c8 ui : add browser-style conversation tabs store Aleksander Grygier 2026-08-17 14:01:12 +02:00
  • bb4caa7540 llama.cpp : bump version to 0.2.0 (#27498) v0.2.0 b10566 Georgi Gerganov 2026-08-21 15:01:24 +03:00
  • c4b0225d85 scripts : add release.sh for release preparation (#27497) Georgi Gerganov 2026-08-21 14:51:26 +03:00
  • 5de25a7487 sync : ggml Georgi Gerganov 2026-08-21 14:32:32 +03:00
  • 01ff204fbd ggml : bump version to 0.21.0 (ggml/1597) Georgi Gerganov 2026-08-21 13:22:00 +03:00
  • 2913a33e9a fit: also take into account n_streams Xuan Son Nguyen 2026-08-21 13:34:31 +02:00
  • 353b32d8b9 ci : remove duplicate flag (#27488) Georgi Gerganov 2026-08-21 14:10:06 +03:00
  • 7a0e42fd01 Revert "sycl : add Q2_K reordered MMVQ and ESIMD kernels (#26336)" (#27486) Georgi Gerganov 2026-08-21 14:02:03 +03:00
  • 5b6ddc9675 ui: Settings navigation cleanup (#27241) Aleksander Grygier 2026-08-21 12:30:03 +02:00
  • e467c2ff61 ci : add nightly-tag.txt to make-release (#27485) Georgi Gerganov 2026-08-21 13:20:44 +03:00
  • d5e61c0331 partially apply to deepseek2 xsn/ggml_rope_off_use Xuan Son Nguyen 2026-08-21 12:07:53 +02:00
  • 1719747451 ci : release clean-up (#27477) Georgi Gerganov 2026-08-21 11:33:40 +03:00
  • 62b2269060 kleidiai : add SME2 F32 GEMV kernel support (#26891) Charles Xu 2026-08-21 10:33:30 +02:00
  • ff14356e0c sycl : add Q2_K reordered MMVQ and ESIMD kernels (#26336) Todd Malsbary 2026-08-21 01:01:40 -07:00
  • 5fff128451 test : make the FA V-is-view-of-K case a test case parameter (#27394) Georgi Gerganov 2026-08-21 10:29:17 +03:00
  • 9e89a196b8 sycl : Add Q5_K ESIMD kernel (#26376) Todd Malsbary 2026-08-21 00:23:02 -07:00
  • cd26896c19 opencl: keep the vocab-scale K-quant lm_head on the CPU for Adreno A7X (compiler issue workaround) (#26440) Hongqiang Wang 2026-08-20 22:30:17 -07:00
  • 1cb3f5eb41 sycl: Update gate logic for Alchemist GPUs regarding OneDNN features. (#26635) HumerousGorgon 2026-08-21 13:16:29 +08:00
  • 6602dd3389 sycl: fix multiple warnings in compiling sycl backend (#26713) Ian Faust 2026-08-21 07:15:40 +02:00
  • 9e96cf77ff sycl : fix load model with mlock issue (#27250) Neo Zhang 2026-08-21 13:14:54 +08:00
  • b2e5e9b28b TP: enable tensor split for LFM2/LFM2MOE (#26993) b10549 Chris Danis 2026-08-21 01:13:58 -04:00
  • a298422da7 docs: fix typos in ET.md (#27457) b10548 vk 2026-08-21 10:06:59 +05:30
  • 450f03946f Merge branch 'master' into xsn/ggml_rope_off_use Xuan Son Nguyen 2026-08-21 00:39:31 +02:00
  • 749f688fca ggml: support ggml_rope_set_offset on opencl, sycl, wgpu, hexagon (#27345) Xuan-Son Nguyen 2026-08-21 00:36:57 +02:00
  • 0e1d9185c5 ci: use shell script to check cmake pkg (#27414) Eve 2026-08-20 20:01:32 +00:00
  • a3f308aa21 Merge remote-tracking branch 'origin/master' into xsn/dots3-note xsn/dots3-note Xuan Son Nguyen 2026-08-20 21:46:53 +02:00
  • a30273376e metal : clamp K extent in tensor API mat-mat kernel for K not a multiple of 32 (#27450) b10545 Georgi Gerganov 2026-08-20 21:31:29 +03:00
  • 6503355df0 opencl: fix q6_K flat mul_mat for Adreno A6x/A7x GPUs with older E031 compilers (#26476) Hongqiang Wang 2026-08-20 10:58:35 -07:00
  • 6b4fa88a6c opencl: fix local size for norm (#27339) lhez 2026-08-20 10:52:07 -07:00
  • c8fe4840e9 ui : use SvelteMap/SvelteSet and fix eslint in drag-and-drop import allozaur/feat/drag-and-drop-json-data-import Aleksander Grygier 2026-08-17 11:05:40 +02:00
  • c81f79e714 ui : fix formatting in drag-and-drop import Aleksander Grygier 2026-08-17 11:00:33 +02:00
  • dd02ae6a6b ui : preview settings diff before importing from Import/Export tab Aleksander Grygier 2026-08-17 09:42:00 +02:00
  • 67adbb18ab ui : add global drag-and-drop import for conversations and settings Aleksander Grygier 2026-08-17 09:41:51 +02:00
  • 0f901faeda ui : fix eslint issues in model selector settings submenu Aleksander Grygier 2026-08-17 11:04:19 +02:00
  • af2b52a145 ui : fix formatting in model selector settings submenu Aleksander Grygier 2026-08-17 11:00:21 +02:00
  • 7d0640a44d ui : add sampling and penalties submenus to model selector Aleksander Grygier 2026-08-16 18:16:48 +02:00
  • ec2a303f3c ui : fix eslint issues in chat form and model selector Aleksander Grygier 2026-08-17 11:04:02 +02:00
  • d79ec3643e ui : fix formatting in chat form and model selector Aleksander Grygier 2026-08-17 10:59:55 +02:00
  • 4c2da7e7c7 feat: Enable microphone input as default for audio models Aleksander Grygier 2026-08-16 18:03:52 +02:00
  • 55df66839f ui : add raw model id tooltip to model selector options Aleksander Grygier 2026-08-15 23:26:25 +02:00
  • 632209f16a ui : make model option hover and focus highlight override the active state Aleksander Grygier 2026-08-15 22:54:05 +02:00
  • d3df967e22 ui : move model list into a submenu within the model selector Aleksander Grygier 2026-08-15 22:53:56 +02:00
  • a5906b7200 ui : add show-org-name-in-trigger display setting Aleksander Grygier 2026-08-15 22:53:48 +02:00
  • c5ee8d0659 ui : keep reasoning submenu visible regardless of model state Aleksander Grygier 2026-08-15 22:53:26 +02:00
  • 46726f077b ui : show reasoning and modality icons on model options and search by modality Aleksander Grygier 2026-08-15 22:53:18 +02:00
  • 9a4662afb1 ui : strip trailing container-format segments from parsed model names Aleksander Grygier 2026-08-15 22:53:04 +02:00
  • 623999274d ui : restore isPrivate for API key masking Aleksander Grygier 2026-08-17 10:59:46 +02:00
  • 1778c97cff ui : derive the syncable parameter list in the parameter sync service Aleksander Grygier 2026-08-15 08:37:44 +02:00
  • 4efe1b9d2a ui : move the settings exit route into ROUTES Aleksander Grygier 2026-08-15 08:36:55 +02:00
  • 1859ad41c0 ui : extract settings localStorage persistence into SettingsService Aleksander Grygier 2026-08-20 13:54:14 +02:00
  • de40f3e81b ui : rework the settings registry into ordered raw-data sections Aleksander Grygier 2026-08-15 08:36:17 +02:00
  • 521a64cd01 ui: Stores split refactor (#27240) Aleksander Grygier 2026-08-20 19:02:04 +02:00
  • 681c29d36a mtmd: add --mmproj-device argument (#23255) b10541 John-Henry Lim 2026-08-21 00:45:37 +08:00
  • 07822bddf8 model : support DSpark for LFM2 models (#27383) Tarek Dakhran 2026-08-20 16:36:57 +02:00
  • 78ec4c3780 vulkan: FA MMQ should use fp32 for Q quantization calculations (#27413) b10539 Jeff Bolz 2026-08-20 09:18:11 -05:00
  • 63b64a50a3 metal : dequant kv cache only for large batches (#27438) b10538 Georgi Gerganov 2026-08-20 17:00:54 +03:00
  • bf0040e15f CI: Use LLVM's OpenMP over MSVC_DEBUG_non_redist on Windows (#26678) b10537 Oliver Simons 2026-08-20 15:42:26 +02:00
  • 9855ad69d3 server: (router) lazy-load startup_models after main setup (#27424) b10536 Xuan-Son Nguyen 2026-08-20 15:22:16 +02:00
  • 8a832e4bf3 server : fix --docker-repo being treated as router mode (#27416) Aritro Bandyopadhyay 2026-08-20 06:37:14 -06:00
  • 2b5621094e CUDA: adding switch points per HW and quant type to tune the mvq->MMQ decode crossover (#26079) b10534 Pranesh Gonegandla 2026-08-20 12:36:21 +00:00
  • f4bd37bd99 nits 2 xsn/server_load_startup_models Xuan Son Nguyen 2026-08-20 14:34:21 +02:00
  • dc64a1620e common : gracefully fallback on unsupported regex patterns in JSON schema (#26939) b10533 Aldehir Rojas 2026-08-20 06:59:03 -05:00
  • 1134adc9bf metal : remove the in-kernel dequantization from the FA kernels gg/metal-fa-remove-quant-kv Georgi Gerganov 2026-08-19 18:56:28 +03:00