vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-08-27 01:04:19 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Commit graph

  • dd4fa6718a dont set_preview_images within abort itself concedo_experimental Concedo 2026-08-26 12:49:10 +08:00
  • ed9d44aa36 lvulkan instead of hardcoded windows lib on non windows Concedo 2026-08-26 00:21:04 +08:00
  • eb6c7376a1 clear old preview when aborted Concedo 2026-08-25 20:56:42 +08:00
  • ad2b22a41d
         sd: set step as 0 for the first noisy preview (#2416) Wagner Bruna 2026-08-25 09:53:15 -03:00
  • 4447017602 Merge branch 'upstream' into concedo_experimental Concedo 2026-08-25 20:44:34 +08:00
  • 3265983620 Merge commit '2fb989b9e7' into concedo_experimental Concedo 2026-08-25 20:30:15 +08:00
  • fe36aa1959 add directio support Concedo 2026-08-24 22:59:18 +08:00
  • b06f828505 mmap and mlock independent Concedo 2026-08-24 22:29:10 +08:00
  • bfd6500450 Merge commit '873e5d8e39' into concedo_experimental Concedo 2026-08-24 21:15:18 +08:00
  • 047b233a9c updated lite Concedo 2026-08-24 19:51:44 +08:00
  • 7584430716
         tests : disable DOTS3NOTE arch test for WebGPU (#27654) upstream fairydreaming 2026-08-24 12:39:31 +02:00
  • 71cc86fa41
         convert: fix GLM regression in index_tensors (#27655) jacekpoplawski 2026-08-24 12:21:00 +02:00
  • a14dba686a
         ggml : shorten virtual device naming in CUDA and Metal (#27608) Georgi Gerganov 2026-08-24 12:35:08 +03:00
  • c1c766da59
         webgpu : reorder includes since V that appears in common_decls.tmpl may be defined as K in flash_attn_decls.tmpl if KV_OVERLAP (#27545) fairydreaming 2026-08-24 10:07:12 +02:00
  • 160c6b0bdd
         mtmd: video: fix moov atom at the end of file (#27596) Xuan-Son Nguyen 2026-08-24 09:59:04 +02:00
  • 985b14912b
         ci : apply ccache-clear with older/min/dry-run to all ccache jobs (#27602) Georgi Gerganov 2026-08-24 10:49:20 +03:00
  • 6036c635e2
         ggml : fix ggml_clamp (#27644) Georgi Gerganov 2026-08-24 10:43:04 +03:00
  • a130532ae1
         mamba2 : Flatten in/out projections to dispatch GEMM instead of GEMV (#27513) Prabhsimran Singh 2026-08-24 11:55:11 +05:30
  • bf0a29cc16
         Deepseek 4: -sm tensor (#26490) Aman Gupta 2026-08-24 11:50:25 +05:30
  • c060ca974c
         model : support MTP in GLM-4.5-Air (#26534) jacekpoplawski 2026-08-23 20:20:44 +02:00
  • ccc8fd2baa
         readme : update links (#27617) Georgi Gerganov 2026-08-23 20:55:56 +03:00
  • d05f89562d
         fix: Change chat tabs nav shortcuts (#27609) Aleksander Grygier 2026-08-23 19:37:19 +02:00
  • 8d9af25633
         test : fix multi-GPU server tests (#27614) Georgi Gerganov 2026-08-23 19:59:42 +03:00
  • 4a08fa2970
         test: move tools/parser to tests (#27548) Xuan-Son Nguyen 2026-08-23 18:38:51 +02:00
  • 56db501e73
         mtmd: use pillow-accurate algo, correct resize_algo for all models (#27594) Xuan-Son Nguyen 2026-08-23 18:35:41 +02:00
  • 95b8e33e16
         ci : add test-llama-archs tensor split for Metal (#27598) Georgi Gerganov 2026-08-23 15:57:07 +03:00
  • a278dcef04
         contrib : recommend waiting for CI before merging (#27603) Niklas Wenzel 2026-08-23 14:56:47 +02:00
  • e8eed4525a
         server : add LLAMA_SERVER_SLOTS_N_DIFF (#27600) Georgi Gerganov 2026-08-23 15:55:51 +03:00
  • ba8e0eddfb
         common : skip device_info loop if it's not going to be printed (#26692) Bartosz Taudul 2026-08-23 14:39:16 +02:00
  • b0539c43ed
         DeepseekV4: fix rollback with multi-seq (#26756) Aman Gupta 2026-08-23 16:27:49 +05:30
  • d3371929bb
         [Tensor parallel] Fix meta tensor split state propagation (#27574) Gaurav Garg 2026-08-23 16:19:12 +05:30
  • 8144f3192e
         ui: Chat Conversation Tabbed navigation (#27263) Aleksander Grygier 2026-08-23 10:46:49 +02:00
  • 6657ded4fa
         vendor : update subprocess.h (#27409) Alessandro de Oliveira Faria (A.K.A.CABELO) 2026-08-23 04:38:29 -03:00
  • 29ea9412a6
         cuda : add POOL_1D support (#27573) Aman Karki 2026-08-23 13:07:32 +05:30
  • 4fd9a4c029 updated lite Concedo 2026-08-23 15:37:31 +08:00
  • 70adb1b4ce
         common: json.h: fix clang lto (#27575) Xuan-Son Nguyen 2026-08-23 01:11:10 +02:00
  • 3f545becce
         vulkan : added the PAD_REFLECT_1D operation (#26586) Safi Ullah 2026-08-23 00:42:20 +05:00
  • 80cff82184 no need backend specific tensor split Concedo 2026-08-23 00:25:53 +08:00
  • b21e4de745
         mtmd: use ggml_rope_set_offset (#27521) Xuan-Son Nguyen 2026-08-22 16:33:47 +02:00
  • d9f918d2d0
         common: add json.h abstraction (#27511) Xuan-Son Nguyen 2026-08-22 16:28:28 +02:00
  • 2fb989b9e7
         fit: also take into account n_streams (#27496) Xuan-Son Nguyen 2026-08-22 16:16:06 +02:00
  • 9fee29e943
         arg: remove -no-cnv from cli [no ci] (#27542) Xuan-Son Nguyen 2026-08-22 15:53:56 +02:00
  • 17fda542d9 cmake missing files Concedo 2026-08-22 19:19:58 +08:00
  • e85caa81ea
         ci : Restore ROCm job for Ubuntu (#27399) Mario Limonciello 2026-08-22 05:28:30 -05:00
  • b6a253517e fix whisper device selection Concedo 2026-08-22 18:16:59 +08:00
  • 2b78904b4a bug fixes for backend code Concedo 2026-08-22 17:28:48 +08:00
  • 2115b73d8e
         model : support DSpark for bailingmoe3 (#27508) Tiwei Bie 2026-08-22 17:19:48 +08:00
  • 54ee5ee643
         mtmd: support dots3-note vision+audio (#27524) Xuan-Son Nguyen 2026-08-22 10:35:50 +02:00
  • 3a653fea93
         ci : add older, min and dry-run options to ccache-clear (#27504) Georgi Gerganov 2026-08-22 11:31:30 +03:00
  • 369e1cd614
         ggml: optimize concat op by replacing per-element memcpy with row-level memcpy (#24575) Kartik Sirohi 2026-08-22 14:00:31 +05:30
  • 2c6b141efb
         common : fix draft-mtp with embeddings (#26352, #27299) (#27400) Shahir BIn Zulfiker 2026-08-22 13:44:22 +06:00
  • 8672290039
         sycl : add Q2_K reordered MMVQ and ESIMD kernels (again) (#27490) Sigbjørn Skjæret 2026-08-22 09:09:26 +02:00
  • 3aeb924628
         readme : fix server badge alt (#27533) Sigbjørn Skjæret 2026-08-22 09:08:07 +02:00
  • 2100e59260
         readme : update badges (#27531) Georgi Gerganov 2026-08-22 08:25:00 +03:00
  • b9b3bbcec1
         refactor: add new module for backend-specific code (#2308) Wagner Bruna 2026-08-21 23:00:00 -03:00
  • d775b8967a
         mtmd: support webp via ffmpeg (#27520) Xuan-Son Nguyen 2026-08-22 01:38:05 +02:00
  • 3af988fabc
         opencl: fold the gpt-oss MoE per-expert bias adds into the epilogue (op/kernel fusion) (#26431) Hongqiang Wang 2026-08-21 14:24:33 -07:00
  • 9a286ac98d
         docs: improve Windows build instructions (#27381) Niklas Wenzel 2026-08-21 20:49:27 +02:00
  • a3b9c23ead
         ci : fix empty release_id in make-release upload step (#27516) Georgi Gerganov 2026-08-21 21:41:25 +03:00
  • 5a32f7b66e
         model: add dots3-note (#27060) Xuan-Son Nguyen 2026-08-21 19:52:34 +02:00
  • 873e5d8e39
         model: use ggml_rope_set_offset() (#27382) Xuan-Son Nguyen 2026-08-21 18:54:29 +02:00
  • d7fa69b7de
         ci : run ccache-clear as the last step of release jobs (#27503) Georgi Gerganov 2026-08-21 18:56:04 +03:00
  • 8c732ca2cc Merge branch 'upstream' into concedo_experimental Concedo 2026-08-21 23:27:27 +08:00
  • 414fadaffc adjust cpu failsafe triggering issue Concedo 2026-08-21 21:48:18 +08:00
  • bb4caa7540
         llama.cpp : bump version to 0.2.0 (#27498) 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
  • 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
  • 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) Chris Danis 2026-08-21 01:13:58 -04:00
  • d42dc9b943 try fix cmake Concedo 2026-08-21 12:57:22 +08:00
  • a298422da7
         docs: fix typos in ET.md (#27457) vk 2026-08-21 10:06:59 +05:30
  • 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
  • a30273376e
         metal : clamp K extent in tensor API mat-mat kernel for K not a multiple of 32 (#27450) 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
  • 521a64cd01
         ui: Stores split refactor (#27240) Aleksander Grygier 2026-08-20 19:02:04 +02:00
  • 681c29d36a
         mtmd: add --mmproj-device argument (#23255) 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) Jeff Bolz 2026-08-20 09:18:11 -05:00
  • 63b64a50a3
         metal : dequant kv cache only for large batches (#27438) Georgi Gerganov 2026-08-20 17:00:54 +03:00
  • bf0040e15f
         CI: Use LLVM's OpenMP over MSVC_DEBUG_non_redist on Windows (#26678) Oliver Simons 2026-08-20 15:42:26 +02:00
  • 9855ad69d3
         server: (router) lazy-load startup_models after main setup (#27424) 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) Pranesh Gonegandla 2026-08-20 12:36:21 +00:00
  • dc64a1620e
         common : gracefully fallback on unsupported regex patterns in JSON schema (#26939) Aldehir Rojas 2026-08-20 06:59:03 -05:00
  • 70aff25250
         metal : dequantize quantized KV to F16 before flash attention (#27390) Georgi Gerganov 2026-08-20 13:43:59 +03:00