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

  • b96487645c ui: media attachments before text (#23467) Saba Fallah 2026-05-25 08:50:41 +02:00
  • 9627d0f540 vendor : update cpp-httplib to 0.45.1 (#23639) Alessandro de Oliveira Faria (A.K.A.CABELO) 2026-05-25 03:45:22 -03:00
  • e2ef8fe42c server: fix checkpoints creation (#22929) jacekpoplawski 2026-05-25 07:56:18 +02:00
  • 6d57c26ef8 perplexity : fix even more integer overflows (#23623) fairydreaming 2026-05-25 07:12:39 +02:00
  • 28123a3937 ci : move most slim jobs to self-hosted runners (#23619) Georgi Gerganov 2026-05-25 08:11:19 +03:00
  • 093f046fd3 updated lite Concedo 2026-05-25 00:25:22 +08:00
  • 9639ab2fb6 support comfy scheduler Concedo 2026-05-25 00:22:40 +08:00
  • e6715b7f8a additional SD aliases for comfyui Concedo 2026-05-24 23:20:44 +08:00
  • 549b9d8433 ci : update build-self-hosted.yml (#23616) Georgi Gerganov 2026-05-24 18:20:10 +03:00
  • 29fd00a7a4 allow accessing tensor split and gpu layers in cpu mode if rpc is in connect mode Concedo 2026-05-24 22:23:51 +08:00
  • 86f6bff620 rpc port to 5551 Concedo 2026-05-24 18:56:23 +08:00
  • 2937fdd823 make send as reference image default for img2img, but with smart fallback for older models. Concedo 2026-05-24 18:34:24 +08:00
  • d774184e9d hacky patch for hidream on kobold to fix tensor type issues Concedo 2026-05-24 16:37:49 +08:00
  • c62d921f0a fix sdcpp build cmake Concedo 2026-05-24 16:14:37 +08:00
  • 5d246a792d convert : minor fixes for numpy 2.x (#23571) Sigbjørn Skjæret 2026-05-24 09:51:31 +02:00
  • 298da8a4c2 Merge remote-tracking branch 'wbruna/kcpp_sd_update_202605_5' into concedo_experimental Concedo 2026-05-24 15:38:37 +08:00
  • 63248fc3e3 cmake : fix ui build (#23592) Aldehir Rojas 2026-05-24 03:37:28 -04:00
  • 83eebe9d08 server: add margin for draft model for fit (#23485) Aman Gupta 2026-05-24 14:43:08 +08:00
  • fff63b5108 TP: fix entirely zero-sized slices per device (#23525) Johannes Gäßler 2026-05-24 08:19:33 +02:00
  • f3061116ff opencl: batch profiling to improve speed and prevent memory leaks (#23495) shaofeiqi 2026-05-23 23:11:43 -07:00
  • 8ca4283f55 Merge branch 'upstream' into concedo_experimental Concedo 2026-05-24 13:55:44 +08:00
  • ae335c4338 fix tools build Concedo 2026-05-24 13:46:36 +08:00
  • 1c0f6db545 hexagon: apply repl optimization in flash attn softmax as #22993 (#23455) Yiwei Shao 2026-05-23 19:56:59 -07:00
  • cec51c7a7d snapdragon: update windows toolchain to use hsdk v6.6.0.0 (#23552) Aparna M P 2026-05-24 08:26:41 +05:30
  • b22ff4b7b4 cmake/ui : refactor the build (#23352) Aldehir Rojas 2026-05-23 17:08:22 -04:00
  • c0c7e147e7 requirements : bump torch to 2.11.0 (#23503) Aditya Singh 2026-05-23 09:24:39 -07:00
  • 38298dd4e8 try to fix cuda builds Concedo 2026-05-23 21:58:01 +08:00
  • 3aea5a795e Revert "fixed incorrect cfg scale returned" Concedo 2026-05-23 21:37:47 +08:00
  • 3ec404b2cb sd: sync to master-646-0baf721 Wagner Bruna 2026-05-22 23:15:29 -03:00
  • 8427efb4c6 sd: sync to master-642-3a8788c Wagner Bruna 2026-05-21 20:46:14 -03:00
  • a0413bdf55 sd: sync to master-637-ef92a00 Wagner Bruna 2026-05-20 22:42:01 -03:00
  • 6c2093e422 sd: sync to master-633-5b0267e Wagner Bruna 2026-05-19 23:37:17 -03:00
  • c28c50e441 sd: sync to master-621-baf7eda Wagner Bruna 2026-05-17 19:45:44 -03:00
  • b0df4c0cfd model : add NVFP4 MTP scale tensors (#23563) Michael Wand 2026-05-23 07:30:31 -04:00
  • a497476330 ggml : Check the right iface method before using the fallback 2d get (#23514) dskwe 2026-05-23 18:49:24 +08:00
  • 9450834335 sd: adjust VAE tile size according to sdtiledvae (#2208) Wagner Bruna 2026-05-23 06:50:44 -03:00
  • ce3aa09b99 cache dir is null Concedo 2026-05-23 17:39:09 +08:00
  • cae0375157 fixed incorrect cfg scale returned Concedo 2026-05-23 17:30:07 +08:00
  • 4bbbd55be6 rpc implementation is complete Concedo 2026-05-23 17:11:30 +08:00
  • 95405ac65f vulkan: fix windows find_package of SPIRV-Headers (#23215) Jeff Bolz 2026-05-23 02:44:46 -05:00
  • 3520b915f9 try revert vae chunk size change Concedo 2026-05-23 09:46:11 +08:00
  • 0f3cb3fc8b opencl: generalize Adreno MoE kernels on M (#23449) Shawn Gu 2026-05-22 17:08:41 -07:00
  • 81553e6524 mmproj overhead estimate calculated but only used on python side Concedo 2026-05-23 00:04:12 +08:00
  • 1acee6bf89 server: only parse empty msg if continuing an assistant msg (#23506) Aldehir Rojas 2026-05-22 11:58:15 -04:00
  • f85cc79526 make swa default on models that support it. removed --useswa, added --noswa Concedo 2026-05-22 23:38:33 +08:00
  • ef570f6308 perplexity : fix integer overflow (#23496) fairydreaming 2026-05-22 14:50:44 +02:00
  • cc9e331213 SYCL: improve MoE prefill throughput (#23142) Alexey Kopytko 2026-05-22 21:50:17 +09:00
  • bcfd1989e9 sycl : Level Zero detection in ggml_sycl_init (#23097) Alexey Kopytko 2026-05-22 21:49:45 +09:00
  • 56f16f235c SYCL : gated_delta_net K>1 (#23174) karavayev 2026-05-22 08:48:56 -04:00
  • 8cc67efcd4 SYCL: add BF16 to DMMV kernel path (~4x tg speedup on Intel Arc) (#21580) Katostrofik 2026-05-22 08:48:24 -04:00
  • 632c41a72f Merge branch 'upstream' into concedo_experimental Concedo 2026-05-22 20:42:51 +08:00
  • 694e8824c5 mmproj autofit reworked Concedo 2026-05-22 20:36:16 +08:00
  • 95feeab52e docs: Update documentation with Granite 4.0/4.1 (#23404) Jesus Talavera 2026-05-22 14:35:46 +02:00
  • 99d4026b11 ggml-zendnn : add Q8_0 quantization support (#23414) Sachin Sharma 2026-05-22 16:46:55 +05:30
  • 9c92e96a64 cmake : build router app only during standalone builds (#23521) fairydreaming 2026-05-22 11:55:29 +02:00
  • afcda09d15 vocab : fix HybridDNA tokenizer (#23466) Kashif Rasul 2026-05-22 11:17:31 +02:00
  • bbce619adb cmake : add install() for impl libraries + fix apple builds (#23511) Georgi Gerganov 2026-05-22 11:46:26 +03:00
  • de6b8f9369 increase ctx slider granularity Concedo 2026-05-22 16:17:54 +08:00
  • 4f0e43da6f CUDA: fix PDL CC check for JIT compilation (#23471) Johannes Gäßler 2026-05-21 23:35:29 +02:00
  • bb28c1fe24 cmake : remove STATIC from impl libraries, enable LLAMA_BUILD_APP by default (#23462) Georgi Gerganov 2026-05-21 21:13:59 +03:00
  • ee7c30578a Update WebGPU support and add link to blog/demo (#23483) Reese Levine 2026-05-21 11:00:27 -07:00
  • 47c0eda9d4 vulkan: fuse snake activation (mul, sin, sqr, mul, add) (#22855) Pascal 2026-05-21 19:39:42 +02:00
  • 718dc159b6 Merge branch 'upstream' into concedo_experimental Concedo 2026-05-21 23:47:21 +08:00
  • 54af9aada9 Merge commit 'e6b4acfe86af380c4e631973b9caa14337954423' into concedo_experimental Concedo 2026-05-21 23:31:32 +08:00
  • 5306f4b3b5 fix(flash-attn): replace f32 with kv_type and q_type (#23372) Chen Yuan 2026-05-21 10:58:49 -04:00
  • 2451feaf69 an easy way to toggle thinking for jinja Concedo 2026-05-21 22:45:33 +08:00
  • 40d5358d3c tests : move save-load-state from examples to tests (#23336) Georgi Gerganov 2026-05-21 14:41:50 +03:00
  • b65bb4baae server: expose prompt token counts in /slots endpoint (#23454) ScrewTSW 2026-05-21 13:29:13 +02:00
  • a1a69f777a metal : optimize concat kernel and fix set kernel threads (#23411) Georgi Gerganov 2026-05-21 13:34:08 +03:00
  • e8bf5b9c6c fixed a potential vuln with onready when combined with admin Concedo 2026-05-21 16:11:28 +08:00
  • 52fb93a2bd server : free draft/MTP resources on sleep to fix VRAM leak (#23461) Aman Gupta 2026-05-21 16:11:11 +08:00
  • c9021714e8 server: re-inject subcommand when router spawns children under unified binary (#23442) Pascal 2026-05-21 10:09:19 +02:00
  • 1d7ab2b947 app : add batched-bench, fit-params, quantize & perplexity (#23459) Adrien Gallouët 2026-05-21 09:29:44 +02:00
  • 12e5d99078 mtp: use inp_out_ids for skipping logit computation (#23433) Aman Gupta 2026-05-21 15:23:14 +08:00
  • 7ea23ddf7b vocab : add Carbon-3B (HybridDNATokenizer) support (#23410) Kashif Rasul 2026-05-21 08:34:32 +02:00
  • 2fc8d1851e doc: fix spec mtp typo (#23435) Ruixiang Wang 2026-05-21 08:30:55 +02:00
  • 5e932a1c8d ui: Improve Git Hooks for UI development (#23403) Aleksander Grygier 2026-05-21 08:27:50 +02:00
  • 2754ce1b3e ggml : Check the right iface method before using the fallback 2d get (#23306) Matt Corallo 2026-05-21 06:24:40 +00:00
  • eeeaf6180b llama-graph: fix null-buffer crash in llm_graph_input_attn_kv_iswa for SWA-only models (#23131) Daniel Elliott 2026-05-20 23:20:51 -07:00
  • 0be84685bd hexagon: ssm-conv fix for large prompts (#23307) Todor Boinovski 2026-05-20 22:14:13 -07:00
  • ce02093fdd app : show version (#23426) Adrien Gallouët 2026-05-21 06:21:13 +02:00
  • f85a747dc0 sd: add backend support for max_vram (#2221) Wagner Bruna 2026-05-21 00:51:00 -03:00
  • 6a257d4463 mtmd, model : merge HunyuanOCR into HunyuanVL and fix OCR vision precision (#23329) wendadawen 2026-05-21 06:35:37 +08:00
  • 3a479c9132 ui: Add max image size option (#22849) stduhpf 2026-05-21 00:00:09 +02:00
  • ad27757261 Move to backend sampling for MTP draft path (#23287) Gaurav Garg 2026-05-20 22:34:45 +05:30
  • 3a6db741a8 opencl: refactor backend initilization (#23318) lhez 2026-05-20 09:57:36 -07:00
  • 510b5c2a35 common/speculative : fix nullptr crash in get_devices_str (#23386) Georgi Gerganov 2026-05-20 19:44:30 +03:00
  • a8681a0ed2 mtmd : DeepSeek-OCR image processing fixes, img_tool::resize padding refactor (#23345) Saba Fallah 2026-05-20 17:37:10 +02:00
  • 095bf63b58 prep for rpc Concedo 2026-05-20 23:29:49 +08:00
  • acd604fb27 vulkan: optimize operations in the IM2COL shader (#22685) Daniele 2026-05-20 17:15:13 +02:00
  • 6ce96713de feat: Add WAV MIME type variants and improve audio format detection (#23396) Aleksander Grygier 2026-05-20 16:55:24 +02:00
  • c9872a2575 hexagon: HMX quantized matmul rework (#23368) Max Krasnyansky 2026-05-20 07:39:01 -07:00
  • e947228222 Programmatic Dependent Launch (PDL) for more performance on newer NVIDIA GPUs (Hopper+) (#22522) Andreas Kieslinger 2026-05-20 13:59:02 +02:00
  • 29f1482221 app : introduce the llama unified executable (#23296) Adrien Gallouët 2026-05-20 13:22:22 +02:00
  • e6b4acfe86 refactor: Move text attachments up before the message content in chat completions payload (#23406) Aleksander Grygier 2026-05-20 13:04:01 +02:00
  • 7d987af23a Merge branch 'upstream' into concedo_experimental Concedo 2026-05-20 18:48:34 +08:00
  • e2b129e1bf mtmd: fit_params now take into account mmproj (#21489) Xuan-Son Nguyen 2026-05-20 11:27:44 +02:00
  • 7e50ef7d79 docker : copy conversion files (#23370) Sigbjørn Skjæret 2026-05-20 11:03:18 +02:00
  • 5028447384 ui: Refactor isMobile as reactive value in viewport store (#23330) Aleksander Grygier 2026-05-20 10:52:00 +02:00
  • 585080d310 fix: Div wrapper no pointer events on hidden (#23390) Aleksander Grygier 2026-05-20 09:46:31 +02:00