Public/koboldcpp
1
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-09-11 23:59:20 +02:00
Code Issues Packages Projects Releases Wiki Activity

Commit Graph

  • 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
  • da4540629a up version Concedo 2026-08-20 18:43:06 +08:00
  • fc84597f96 Merge commit '533b18257b7da879a5de39f5d6437041e0e42c39' into concedo_experimental Concedo 2026-08-20 18:42:18 +08:00
  • f20395dae5 Revert "tensor-split meta backend fixes (#26502)" (#27433) Georgi Gerganov 2026-08-20 13:35:15 +03:00
  • f0cd0225aa Merge commit '34af94cd9ab277632e27caeec2d41de2fd091b31' into concedo_experimental Concedo 2026-08-20 17:08:46 +08:00
  • 8497981321 ggml: fix backend split scheduler race condition (#26040) Ruben Ortlam 2026-08-20 10:42:33 +02:00
  • a3b1effcda convert: fix get block count error for Nemotron 3 Ultra (#27101) Rock Chen 2026-08-20 15:35:28 +08:00
  • d9b6be07d0 ggml-cuda: provide static workspace for cuBLAS handles (#26574) Alexander Heisler 2026-08-20 03:27:51 -04:00
  • 929d47a391 graph : create V as a view of K in the k_iswa build_attn (#27392) Georgi Gerganov 2026-08-20 10:00:35 +03:00
  • f466cfa38f spec : avoid binding reference to null pointer (#27404) Georgi Gerganov 2026-08-20 10:00:16 +03:00
  • 2cfdb5fc08 vulkan : add source groups for shaders (#26666) Markus Tavenrath 2026-08-20 08:52:28 +02:00
  • 1fc6e11ab8 minor fix for erquint Concedo 2026-08-20 13:21:46 +08:00
  • 9ee9fc04c1 opencl: make the MoE expert scatter deterministic (#26464) Hongqiang Wang 2026-08-19 20:40:19 -07:00
  • d59d455fd8 tensor-split meta backend fixes (#26502) Max Krasnyansky 2026-08-19 14:53:27 -07:00
  • 990e3bfee3 hexagon: fix FA HMX queue ordering and pack the rescale D matrices (#27042) Yiwei Shao 2026-08-19 14:42:57 -07:00
  • b062ba735e opencl: port fused ssm_scan kernel (Mamba-2, d_state in {128, 256}) to GPU (#26439) Hongqiang Wang 2026-08-19 13:35:17 -07:00
  • cd644c3954 ggml-cpu: gate __fp16 on __ARM_FP16_FORMAT_IEEE (#26860) Pascal 2026-08-19 22:03:13 +02:00
  • 947fd9bb2b server: refactor sleep handling, allow access /metrics during sleep (#27376) Xuan-Son Nguyen 2026-08-19 20:48:09 +02:00
  • ee0ea03adf server : make models endpoints private when authentication is enabled (#26347) s0mecode 2026-08-19 22:44:42 +04:00
  • dc72703fc6 vulkan : dequant q8_0 KV once in coopmat1 (#25494) Nathanw1014 2026-08-20 01:14:15 +09:30
  • b95502ba9a vulkan: add null checks in ggml_vk_queue_command_pools_cleanup (#27353) Jetson Tan 2026-08-19 23:43:10 +08:00
  • 3e7344670a Revert "common: share thread pools when n_threads differ (#27138)" (#27337) Niklas Wenzel 2026-08-19 17:05:48 +02:00
  • 7221e24f57 model : GraniteSWAForCausalLM / GraniteMoeSWAForCausalLM (#25505) Gabe Goodhart 2026-08-19 08:53:31 -06:00
  • 6cc504a2e9 sycl: report zero devices instead of aborting when the host has none (#27291) Titaniumtown 2026-08-19 07:46:01 -07:00
  • 01ac3ad761 ci : add release attestation url (#27389) Sigbjørn Skjæret 2026-08-19 16:40:47 +02:00
  • 2e92ecd024 models : remove duplicate metadata load (#27378) Sigbjørn Skjæret 2026-08-19 16:05:50 +02:00
  • 645ca2834b ci : re-enable release dependency for sycl (#27385) Sigbjørn Skjæret 2026-08-19 15:44:16 +02:00
  • fe8156f789 ggml: add ggml_rope_set_offset (+ metal support) (#27120) Xuan-Son Nguyen 2026-08-19 14:04:57 +02:00
  • 77acca437f ui: read persisted settings before the API key probe (#27365) Pascal 2026-08-19 14:02:08 +02:00
  • 95c409c136 mtmd: add mtmd_bitmap_set_mergeable (#27348) Xuan-Son Nguyen 2026-08-19 13:48:22 +02:00
  • 8ef78e644f metal : dequantize q8_0 using packed types (#27370) Georgi Gerganov 2026-08-19 14:10:05 +03:00
  • ee4c505a4f server: add dedup-cache-models preset option (#27346) Xuan-Son Nguyen 2026-08-19 11:04:26 +02:00
  • 98d1e92c21 vulkan: tiled transpose for 0<->2 permuted CONT (#26585) Kevin Hopper 2026-08-19 03:20:21 -05:00
  • 5112b9738b ggml-webgpu: add mulmat with overlapping src0/src1 (e.g., for minimax-01) (#27321) Masashi Yoshimura 2026-08-19 16:29:33 +09:00
  • 0adcc3bb57 ci : add attestation for signed release artifacts (#25933) Jeremie Miller 2026-08-19 01:23:52 -06:00
  • 79fe799194 tests: skip test-unicode build on win32/BUILD_SHARED_LIBS (#27336) Jeff Bolz 2026-08-19 01:50:50 -05:00
  • 0329fcdac8 gguf-py : add size guards to GGUFReader (#27188) Oğuzhan Akkaya 2026-08-19 02:35:27 -04:00
  • 6d05498314 server: (cosmetic) do not print cmd_child_to_router messages [no release] (#27347) Xuan-Son Nguyen 2026-08-19 01:45:56 +02:00
  • 60addddf3c opencl: fix WAR race in the generic FA tile kernels when the WG spans subgroups (#26434) Hongqiang Wang 2026-08-18 13:57:24 -07:00
  • 9731ad3f29 mtmd: deepseek-ocr SAM ggml_conv_2d with the im2col kept in F32 (#26727) Saba Fallah 2026-08-18 19:05:19 +02:00
  • af5172627d RPC: populate use_count to enable fusion inside backends (#27142) Aman Gupta 2026-08-18 21:08:57 +05:30
  • 3dc7285b4f ui: Services consolidation refactor (#27239) Aleksander Grygier 2026-08-18 16:39:32 +02:00
  • fdf4c64604 ui: Stores consolidation refactor (#27238) Aleksander Grygier 2026-08-18 16:37:26 +02:00
  • 04b569142d common: share thread pools when n_threads differ (#27138) Niklas Wenzel 2026-08-18 16:23:43 +02:00
  • 0596704284 quant : Optimise memory usage by evicting weights after processing each layer (#22877) Ed Addario 2026-08-18 15:22:32 +01:00
  • 0882c7bc89 sycl: honor GGML_HINT_SRC0_IS_HADAMARD (#27298) Titaniumtown 2026-08-18 06:21:25 -07:00
  • afd439df1f unicode : include '~' in collapsed symbol class (#26972) Thiago Padilha 2026-08-18 10:15:22 -03:00
  • 169e4a7ff2 readme : update status badges + regen AUTHORS (#27317) Georgi Gerganov 2026-08-18 14:35:04 +03:00
  • 5b80635beb fix for https://github.com/LostRuins/koboldcpp/security/advisories/GHSA-qhvp-gj7g-rw26 Concedo 2026-08-18 18:20:05 +08:00
  • 493f6e6d9c sd: fix progress report for second order samplers (#2403) Wagner Bruna 2026-08-18 07:18:58 -03:00
  • 9d77fa1725 ci : Update OpenVINO to 2026.3, skip nemotron-h rollback test (#27292) Zijun Yu 2026-08-18 18:02:22 +08:00
  • c0296022f3 ci: add Windows ARM64 CUDA support to the manual workflow (#27300) shivamkumard-ctrl 2026-08-18 15:25:45 +05:30
  • 7acdbb1f19 mtmd: fix LFM2 image tiling threshold (#27057) BlackFoil 2026-08-18 18:11:19 +09:00
  • 1511ce3bc3 sync : ggml Georgi Gerganov 2026-08-18 11:29:14 +03:00
  • da786dc23e ggml : bump version to 0.20.2 (ggml/1589) Georgi Gerganov 2026-08-18 11:28:01 +03:00
  • 27e345b574 build : fix xcframework + cmake clean-up (#27304) Georgi Gerganov 2026-08-18 11:16:51 +03:00
  • 8b86400975 ci : create pre-release with change log and nightly link in make-release (#27302) Georgi Gerganov 2026-08-18 10:14:41 +03:00
  • 25ae3a9b33 CUDA: MMVQ nwarps=8 for bs=1 for dense models on DGX Spark (#26843) ynankani 2026-08-18 04:15:53 +00:00
  • 01818e4956 ui: enforce alphabetical enum member ordering (#27272) Aleksander Grygier 2026-08-17 23:52:00 +02:00
  • 0021a77de0 ui: Refactor Built-In Tools naming (Server/Browser) (#27271) Aleksander Grygier 2026-08-17 22:23:22 +02:00
  • 058df671b2 ci: more optimizations (#26983) Eve 2026-08-17 19:59:40 +00:00
  • 087f94d82e doc: document MCP stdio servers and CORS defaults in the server README [no release] [no ci] (#26847) Pascal 2026-08-17 21:32:15 +02:00
  • 533b18257b server: save processed mtmd chunks as placeholder (#27278) Xuan-Son Nguyen 2026-08-17 21:29:50 +02:00
  • ed1c3a20f5 mtmd: use sha256 for input hashing (#27274) Xuan-Son Nguyen 2026-08-17 21:20:12 +02:00
  • d8df12ebc4 vocab : support integer tokenizer scores (#27260) Sigbjørn Skjæret 2026-08-17 20:13:15 +02:00
  • b75ecd1971 mtmd : skip thumbnail for non-tiled LFM2 images (#27246) Tarek Dakhran 2026-08-17 19:41:32 +02:00
  • 60eeeb6082 cuda : skip UMA override for HIP builds (#27083) Mario Limonciello 2026-08-17 11:35:36 -05:00
  • 39be55c97e vendor: move hash to vendor (#27262) Xuan-Son Nguyen 2026-08-17 18:21:02 +02:00
  • 34af94cd9a ci : push release tag explicitly in release.yml (#27261) Georgi Gerganov 2026-08-17 16:14:13 +03:00
  • 666f8898a2 ui: move get_datetime tool to frontend (#27255) Xuan-Son Nguyen 2026-08-17 14:33:55 +02:00
  • 805984d676 ci : reduce builds in build-xcframework.sh (#27252) Georgi Gerganov 2026-08-17 14:53:21 +03:00
  • 9cd719af21 model: support speculators-format checkpoints for DSpark (#26275) 王金旭 2026-08-17 19:51:06 +08:00
  • 7077abbe14 ui: add browser get_info tool (#27251) Xuan-Son Nguyen 2026-08-17 13:14:33 +02:00
  • d83f72d463 ci : restore release.yml check during make-release.yml (#27247) Georgi Gerganov 2026-08-17 13:10:56 +03:00
  • 9f0d017efb mtmd: harden preprocessor_granite (#27235) Xuan-Son Nguyen 2026-08-17 11:30:15 +02:00
  • 7c35571e5d ci : allow make-release to target a specific commit (#27234) Georgi Gerganov 2026-08-17 11:52:46 +03:00
  • f9779dda86 ci : make release workflows use a deploy key (#27229) Georgi Gerganov 2026-08-17 11:31:20 +03:00
  • fa88ae9368 convert: add @ModelBase.example (#27208) Xuan-Son Nguyen 2026-08-17 10:15:11 +02:00
  • 3733366720 model : BailingMoE3 Support (#26608) Toby 2026-08-17 03:49:49 -04:00
  • 4197155add sync : ggml Georgi Gerganov 2026-08-17 09:46:25 +03:00
  • cea66f4c5a ggml : bump version to 0.20.1 (ggml/1587) Georgi Gerganov 2026-08-17 09:45:11 +03:00
  • 4695f001fe llama-bench: fix deprecation warnings missing trailing newline (#27179) Fathi Boudra 2026-08-17 06:33:24 +02:00
  • f275595dd1 sycl: fix thread/block count in quantized cpy kernel launches (#27160) Titaniumtown 2026-08-16 21:32:16 -07:00
  • 37a215c9e9 [SYCL] support OP OPT_STEP_ADAMW, OPT_STEP_SGD (#25268) Neo Zhang 2026-08-17 12:31:29 +08:00
  • c27396c8be remove unused workflow Concedo 2026-08-16 21:22:57 +08:00
  • 4df29be4f4 ci : fix dry-run reporting in make-release job [no ci] (#27167) Daniel Bevenius 2026-08-16 14:53:13 +02:00
  • 3cb7ffb1a1 model : remove some ggml_concat (#27176) fairydreaming 2026-08-16 14:12:55 +02:00
  • b94041a98e chat: refactor handling supports_string_content / supports_typed_content (#27130) Xuan-Son Nguyen 2026-08-16 12:45:33 +02:00
  • 10bf611e53 llama : check LoRA tensor data is within file bounds (#27056) Oğuzhan Akkaya 2026-08-16 02:38:01 -04:00
  • ce26e55e77 updated sdui Concedo 2026-08-16 12:19:51 +08:00
  • ece963f41b ui: mask API Key field in settings and error splash to stop browser a… (#26562) Cristiano Pinto 2026-08-15 21:52:55 +01:00