Public/koboldcpp
1
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-09-15 03:08:49 +02:00
Code Issues Packages Projects Releases Wiki Activity

Commit Graph

  • 5aa3a64596 nix : add nix-nodejs facilities to build Web UI (#23846) Christian Hoener zu Siederdissen 2026-06-01 20:01:26 +02:00
  • 27d9ed8397 opencl: add basic support for q5_0 and q5_1 (#23548) shaofeiqi 2026-06-01 10:06:50 -07:00
  • 335abed17d vendor : update cpp-httplib to 0.46.1 (#23980) Adrien Gallouët 2026-06-01 18:40:10 +02:00
  • de6f727aae llama: limit max outputs of llama_context (#23861) Aman Gupta 2026-06-01 23:01:38 +08:00
  • 95b8b8ec1a metal: template GLU kernels to support f16/f32 (#23882) Shrivas Shankar 2026-06-01 07:40:28 -05:00
  • 55ac0909e5 vulkan: don't hold the device mutex while compiling pipelines (#23641) Jeff Bolz 2026-06-01 07:04:01 -05:00
  • bef69f1306 vulkan: reduce host memory lock contention (#23376) Winston Ma 2026-06-01 20:03:32 +08:00
  • 5aba5364d9 vocab: add normalizer.lowercase support to WPM (#23899) o7si 2026-06-01 19:26:47 +08:00
  • 241ece07c3 disable temporal tiling Concedo 2026-06-01 18:34:27 +08:00
  • 8e6fff84de TP: quantized KV cache support (#23792) Johannes Gäßler 2026-06-01 12:30:10 +02:00
  • 02a57017f6 security : disable private disclosures (#23963) Georgi Gerganov 2026-06-01 13:14:12 +03:00
  • 48b88c3b00 model: Add EXAONE 4.5 implementations (#21733) Junwon Hwang 2026-06-01 18:48:53 +09:00
  • 19620004f5 vulkan: Block-load Q3_K/Q6_K block data and subtract on 32b ints (#23056) Matt Corallo 2026-06-01 09:46:48 +00:00
  • f8c0a19d46 vulkan: Removed unused functions (#23175) Winston Ma 2026-06-01 17:46:23 +08:00
  • 19b5f811c3 allow up to 32 fps Concedo 2026-06-01 17:37:46 +08:00
  • 5254a7994d common : support manually triggering the reasoning budget end sequence (#23949) Aldehir Rojas 2026-06-01 05:37:11 -04:00
  • f4186b767b up version Concedo 2026-06-01 16:26:20 +08:00
  • c3246cd392 allow SD to limit max VRAM usage Concedo 2026-06-01 16:06:27 +08:00
  • e22b0de60d ci : add missing Linux label to cpu-x64-high-perf runner (#23958) Georgi Gerganov 2026-06-01 10:39:59 +03:00
  • a51142497a [SYCL] Support Q4_1, Q5_0, Q5_1 in Flash-attention (#23812) Neo Zhang 2026-06-01 14:53:53 +08:00
  • 4162522688 [SYCL] Add more types in GET_ROWS OP (#23710) Neo Zhang 2026-06-01 14:53:04 +08:00
  • 44e211cecf sycl : Optimize Q3_K mul_mat by reorder (#23725) Neo Zhang 2026-06-01 14:50:55 +08:00
  • af6528e6df ci: remove redundant or duplicate jobs (#23927) Eve 2026-06-01 03:32:17 +00:00
  • 485113f74c low default vae tiling to 640 Concedo 2026-06-01 10:50:31 +08:00
  • 6f165c1c64 server : handle If-None-Match weak ETags (#23916) Eric Zhang 2026-06-01 05:21:08 +08:00
  • 399739d5c5 ci : limit trigger paths for the CPU workflow (#23938) Georgi Gerganov 2026-05-31 19:02:47 +03:00
  • 14b7da5e44 allow reversing the reference image Concedo 2026-05-31 23:08:58 +08:00
  • d4c8e2c29c vocab : add tokenizer support for jina-embeddings-v2-base-zh (#18756) o7si 2026-05-31 18:37:35 +08:00
  • fcceb68f3f allow fallback plan with LLM Concedo 2026-05-31 17:22:42 +08:00
  • 3292da09f6 ui: fix ETag truncation with MSVC compiler (#23917) Eric Zhang 2026-05-31 17:21:23 +08:00
  • e6123e2080 docs : update ZenDNN docs for Q8 support (#23791) Vladislav 2026-05-31 11:26:42 +03:00
  • e9d670e203 solve some warnings v1.114.1 Concedo 2026-05-31 15:10:48 +08:00
  • 22cadc1944 llama: only use one iGPU device by default (#23897) Ruben Ortlam 2026-05-31 08:17:47 +02:00
  • 2f100fe3d1 sd: sync to master-660-d2797b8 (#2241) Wagner Bruna 2026-05-31 03:04:25 -03:00
  • f90d9240f1 fixed auto gpu selection issues Concedo 2026-05-31 14:00:46 +08:00
  • d749821db3 webui: add custom CSS injection via config (#23904) Pascal 2026-05-30 23:49:31 +02:00
  • aa46bda89b Support -fa auto in llama-bench (#23714) Gaurav Garg 2026-05-31 02:03:57 +05:30
  • c1b817032e Merge branch 'upstream' into concedo_experimental Concedo 2026-05-31 02:06:39 +08:00
  • 478e64e549 update sdui Concedo 2026-05-31 02:00:52 +08:00
  • 4cd3888e9b increase frame limit Concedo 2026-05-31 01:30:43 +08:00
  • cc9490d9b0 default embed max ctx to 4096 Concedo 2026-05-31 01:23:54 +08:00
  • d6588daa80 opencl: support bf16 by converting to f16 (#23839) lhez 2026-05-30 10:17:47 -07:00
  • 5a4a3a34cb allow setting backend automatically even if model is unset but sdmodel is set Concedo 2026-05-31 00:54:59 +08:00
  • 3361ef801c video vae tiling fix Concedo 2026-05-30 22:59:15 +08:00
  • d38d50e7ff ui: exclude generated build dirs from prettier and eslint so lint errors stop being masked (#23910) Pascal 2026-05-30 16:50:54 +02:00
  • 8b0e0db606 TP: fix granularity for Qwen 3.5/3.6 + 3 GPUs (#23843) Johannes Gäßler 2026-05-30 15:48:00 +02:00
  • 2d9b7c8e98 metal : restore im2col implementation for large kernels (#23901) Georgi Gerganov 2026-05-30 15:26:13 +03:00
  • e674b1279b test: (test-llama-archs) log the config name first (#23885) Xuan-Son Nguyen 2026-05-30 12:22:38 +02:00
  • 4c4e91b799 ci : update ios-xcode release job to macos-26 (#23906) Georgi Gerganov 2026-05-30 13:21:46 +03:00
  • d48a56effb ggml : add some lsx support (#23798) Jinyang He 2026-05-30 16:53:26 +08:00
  • 6e093b80ea vulkan: add Flash Attention support for BFloat16 KV cache (#23420) Ruben Ortlam 2026-05-30 10:39:31 +02:00
  • d4b513c19d mmap fix from https://github.com/leejet/stable-diffusion.cpp/pull/1575 v1.114 Concedo 2026-05-30 16:12:34 +08:00
  • 337528571d ci : fix s390x release job (#23898) Georgi Gerganov 2026-05-30 09:21:38 +03:00
  • d4204b03a5 ci : clear cache instead of "no timestamp" keys + fix macos (#23895) Georgi Gerganov 2026-05-30 08:52:30 +03:00
  • 33c539b452 updated sdui (+1 squashed commits) Concedo 2026-05-30 11:48:52 +08:00
  • 1738129bee llama : do not skip iGPU when only RPC devices are present (#23868) Radoslav Gerganov 2026-05-30 07:48:22 +03:00
  • 5dc1a89001 support final frame Concedo 2026-05-30 09:27:51 +08:00
  • c30a386932 fix tools build Concedo 2026-05-30 08:55:37 +08:00
  • 0821c5fcfd server: in SSE mode, send HTTP headers when slot starts (#23884) Xuan-Son Nguyen 2026-05-30 00:06:29 +02:00
  • 151f3a98e9 ggml-webgpu: Check earlier for WebGPU required features (#23879) Reese Levine 2026-05-29 14:16:05 -07:00
  • b22da25889 ggml-webgpu: add q4_0/q8_0 SET_ROWS (#23760) Reese Levine 2026-05-29 14:14:11 -07:00
  • 689a9a470e server-bench : add speed-bench for speculative decoding benchmarking (#23869) Ruixiang Wang 2026-05-29 23:09:47 +02:00
  • 5a46b46acd app: add llama update self updater (#23865) Pascal 2026-05-29 23:02:40 +02:00
  • 22d66b567e ui: handle audio/vnd.wave as audio WAV file (#23754) ValdikSS 2026-05-29 22:41:35 +03:00
  • 2084434e66 vocab : support tokenizer for LFM2.5-8B-A1B (#23826) Tarek Dakhran 2026-05-29 20:25:43 +02:00
  • 5ff74fe9a6 remove unused action Concedo 2026-05-30 01:58:16 +08:00
  • 79c21d87f0 tool builds need extra folder now Concedo 2026-05-30 01:56:16 +08:00
  • 764f1e64a1 graph : ensure DS32 kq_mask_lid is F32 (#23864) Sigbjørn Skjæret 2026-05-29 19:55:14 +02:00
  • e541554d70 Merge branch 'upstream' into concedo_experimental Concedo 2026-05-30 01:54:53 +08:00
  • b5f52280fb server: remove obsolete scripts (#23870) Xuan-Son Nguyen 2026-05-29 19:47:30 +02:00
  • dc71236b6c ci : update macos release to use macos-26 runner (#23878) Georgi Gerganov 2026-05-29 20:41:57 +03:00
  • baacd640c0 Merge commit 'dd1557907ae50e11814e25609b30825b67963663' into concedo_experimental Concedo 2026-05-30 01:40:09 +08:00
  • b427dde1a5 increase total frame cap once more to 160 Concedo 2026-05-30 01:34:43 +08:00
  • 6605dce5ce fix ltx assert for cpu vae Concedo 2026-05-30 01:24:23 +08:00
  • 48a6d161a5 add fps controls Concedo 2026-05-29 23:18:14 +08:00
  • 06d26dfdff download: add option to skip_download (#23059) Xuan-Son Nguyen 2026-05-29 16:30:55 +02:00
  • da3f990a47 mtmd: Add DeepSeekOCR 2 Support (#20975) Saba Fallah 2026-05-29 16:13:51 +02:00
  • 272c1ee232 increase frame limit to 120 and allow loading tae ltx Concedo 2026-05-29 18:50:01 +08:00
  • 6ed481eea4 CUDA: Check PTX version on host side to guard PDL dispatch (#23530) Oliver Simons 2026-05-29 12:28:18 +02:00
  • cb47092b00 server: bump timeout to 3600s (#23842) Xuan-Son Nguyen 2026-05-29 10:23:17 +02:00
  • 1f0aa2a696 model : support for DeepseekV32ForCausalLM with generic DeepSeek Sparse Attention (DSA) implementation (#23346) fairydreaming 2026-05-29 10:15:17 +02:00
  • 031ddb2e08 llama: use f16 mask for FA to save VRAM (#23764) Aman Gupta 2026-05-29 15:44:43 +08:00
  • fe12e422ad sync : ggml Georgi Gerganov 2026-05-29 09:53:41 +03:00
  • ea02bc37f5 ggml : bump version to 0.13.1 (ggml/1523) Georgi Gerganov 2026-05-29 09:46:12 +03:00
  • b000431a0b ngram-mod : Add missing include (#23857) Omid Azizi 2026-05-28 23:21:37 -07:00
  • eef59a7642 llama: add llm_graph_input_mtp (#23643) Aman Gupta 2026-05-29 14:17:32 +08:00
  • 8ddb4fedb1 add audio support Concedo 2026-05-29 13:49:30 +08:00
  • 98e480a32e app : move licences to llama-app (#23824) Adrien Gallouët 2026-05-29 07:46:11 +02:00
  • 241cbd41d2 cuda : disables launch_fattn PDL enrollment due to compiler bug (#23825) Andreas Kieslinger 2026-05-29 06:46:10 +02:00
  • 33c718db1f meta : Add missing buffer set in allreduce fallback !COMPUTE clear (#23480) Matt Corallo 2026-05-29 03:30:24 +00:00
  • 9149e6a96e fix for ltx Concedo 2026-05-29 10:49:04 +08:00
  • 19e92c33ef hexagon: basic/generic op fusion support and RMS_NORM+MUL fusion (#23835) Max Krasnyansky 2026-05-28 14:05:54 -07:00
  • 751ebd17a5 mtmd-debug: add color and rainbow mode (#23829) Xuan-Son Nguyen 2026-05-28 20:59:14 +02:00
  • c8914ad4f4 mtmd: fix gemma 4 projector pre_norm (#23822) Xuan-Son Nguyen 2026-05-28 20:58:55 +02:00
  • 408ae2b9e5 opencl: move backend info printing into its own function (#23702) lhez 2026-05-28 11:05:42 -07:00
  • 3ef2369551 ci : run ui publish on ubuntu-slim (#23818) Sigbjørn Skjæret 2026-05-28 19:58:32 +02:00
  • 2f6c815dc4 ui: fix audio and video modality detection (#23756) ValdikSS 2026-05-28 18:36:10 +03:00
  • 445b7cef62 ci : releases use Github-hosted builds for the UI (#23823) Georgi Gerganov 2026-05-28 17:50:32 +03:00
  • 13663730a9 ltx wip Concedo 2026-05-28 22:45:24 +08:00
  • 479a9a1b03 app : improve help output (#23805) Adrien Gallouët 2026-05-28 16:45:06 +02:00