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

  • 1593d5684d docker : support specifying the GCC version for CUDA (#24447) wencan 2026-06-12 05:12:09 +08:00
  • 4c6595503f vulkan: ifdef eMesaHoneykrisp (build fix) (#24479) Jeff Bolz 2026-06-11 13:22:17 -05:00
  • 263cc04a54 sync : ggml Georgi Gerganov 2026-06-11 19:33:33 +03:00
  • 17e59d6209 ggml : bump version to 0.15.0 (ggml/1539) Georgi Gerganov 2026-06-11 19:32:38 +03:00
  • 60d0e70d76 RNN lifeboat implementation Concedo 2026-06-11 23:40:43 +08:00
  • 7d1147bc35 smartcache improvements Concedo 2026-06-11 22:48:37 +08:00
  • 79331fd382 fixed mtp for qwen Concedo 2026-06-11 22:04:31 +08:00
  • fdc3db9b65 vulkan: add fast path for contiguous buffer transfers (#23973) Winston Ma 2026-06-11 21:46:25 +08:00
  • 1af154a76f vulkan: use medium matmul tile on Asahi Linux (#24306) Kevin Liu 2026-06-11 09:43:04 -04:00
  • 18ef86ecec server: skip unused log lines on router mode (#24463) Xuan-Son Nguyen 2026-06-11 11:36:35 +02:00
  • 1bfbdb134e vocab : adopt leading TemplateProcessing special token as BOS (#24428) o7si 2026-06-11 15:37:23 +08:00
  • 68f30663cf vocab : refactor normalizer flags into options struct, add strip_accents (#24371) o7si 2026-06-11 15:36:50 +08:00
  • 40084bb1f8 mtp drafting added (+1 squashed commits) Concedo 2026-06-11 15:11:41 +08:00
  • db94854ff5 server : skip checkpoints beyond pos_next (#24411) Aldehir Rojas 2026-06-11 02:18:12 -05:00
  • 10e4b6d5e3 support gemma assistant as a draft model Concedo 2026-06-11 12:16:43 +08:00
  • ac4cddeb0d vendor : update LibreSSL to 4.3.2 (#24397) Adrien Gallouët 2026-06-10 22:28:03 +02:00
  • e95dae18d6 Remove padding and multiple D2D copies for MTP (#24086) Gaurav Garg 2026-06-10 23:21:16 +05:30
  • a860ec0b37 Merge branch 'upstream' into concedo_experimental Concedo 2026-06-10 23:16:06 +08:00
  • d2462f8f7a chat: fix LFM2/LFM2.5 ignoring json_schema (#24377) Tarek Dakhran 2026-06-10 14:41:41 +02:00
  • fb83cc9a07 CUDA: Fix ssm_scan_f32 data-races (#24360) Oliver Simons 2026-06-10 14:27:08 +02:00
  • e8ead6efaa increase ctx and gen amt defaults Concedo 2026-06-10 18:00:26 +08:00
  • afc8de2c6b Merge branch 'upstream' into concedo_experimental Concedo 2026-06-10 17:21:05 +08:00
  • 039e20a2db ci : bump komac version (#24396) Sigbjørn Skjæret 2026-06-10 09:45:20 +02:00
  • d2e22ed975 speculative : fix "ngram-map-k4v" name in logging (#24253) ddh0 2026-06-10 02:31:35 -05:00
  • 258ca8fd90 fix build Concedo 2026-06-10 10:33:06 +08:00
  • 8cf8469bb8 reasoningeffort param Concedo 2026-06-10 10:30:57 +08:00
  • 76da2450a4 webui: implement pinned conversations support (#21387) Rémy Mathieu 2026-06-09 21:33:22 +02:00
  • d73cd07674 graph: Fix granite speech model inference by applying embedding scale when deepstack is not used (#24357) Aarnav Pai 2026-06-09 23:16:27 +05:30
  • e839598185 think effort box Concedo 2026-06-10 01:32:42 +08:00
  • dd2f966f4b Merge commit 'c2b1518fd4834bdd255a8ad9639738de3fb7d4ef' into concedo_experimental Concedo 2026-06-10 00:56:44 +08:00
  • 6bae15da71 fix build, remove clip quantize (+1 squashed commits) Concedo 2026-06-10 00:36:43 +08:00
  • e25a32e98c ci : fix windows release (#24369) Sigbjørn Skjæret 2026-06-09 18:42:23 +02:00
  • cd49b19016 Merge branch 'upstream' into concedo_experimental Concedo 2026-06-10 00:36:26 +08:00
  • 483609509d ui: add opt-in run_javascript frontend tool (#24244) Pascal 2026-06-09 18:02:31 +02:00
  • fe13a2989d migration to mtmd complete Concedo 2026-06-09 23:09:45 +08:00
  • 0740ce70b7 revert incorrect token count for mtmd Concedo 2026-06-09 22:46:17 +08:00
  • ac8e77d82e Revert "cleanup round 2" Concedo 2026-06-09 22:33:00 +08:00
  • da0ba5cefd Revert "cleanup round 3" Concedo 2026-06-09 22:32:42 +08:00
  • 49f3542190 mtmd: build_vit batching (#24352) Saba Fallah 2026-06-09 16:32:08 +02:00
  • 0ead9907f0 cleanup round 3 Concedo 2026-06-09 21:52:46 +08:00
  • c7e39f9c97 cleanup round 2 Concedo 2026-06-09 21:49:20 +08:00
  • f5acccad63 cleanup round 1 Concedo 2026-06-09 21:13:48 +08:00
  • d6d0ce8215 vulkan: reduce iq1 shared memory usage for mul_mm (#24287) Jeff Bolz 2026-06-09 06:27:38 -05:00
  • b4e3dc613b vulkan: add v_dot2_f32_f16 support in matrix-matrix multiplication and Flash Attention (#24123) Ruben Ortlam 2026-06-09 13:27:04 +02:00
  • ae735b1314 ui: Fix excessive style recalculation on hover (#24243) Nick Towle 2026-06-09 03:52:20 -07:00
  • 9682e351b8 mtmd: refactor video subproc handling (#24316) Xuan-Son Nguyen 2026-06-09 12:15:12 +02:00
  • 1e912561dd server: log prompts to directory (#22031) jacekpoplawski 2026-06-09 12:09:07 +02:00
  • 90a14cecf8 mtmd checkpoint 2 Concedo 2026-06-09 17:55:17 +08:00
  • efbacf8d21 ui: fix mobile chat form overflow and bust stale bundle cache (#24158) Pascal 2026-06-09 11:12:58 +02:00
  • 26021699bc ggml : add GGML_OP_COL2IM_1D (#24206) Pascal 2026-06-09 11:01:37 +02:00
  • 794a271cfa upgrade to mtmd checkpoint 1 Concedo 2026-06-09 16:06:30 +08:00
  • 961e9a3e46 server : do not clear slots without unified KV cache (#24190) fiesh 2026-06-09 09:45:16 +02:00
  • f0152efe40 models : fix plamo2 attention_key/value_length regression (#24317) Sigbjørn Skjæret 2026-06-09 09:26:44 +02:00
  • fd3271e0b4 ggml-cpu : fix rms_norm_back wrong output under in-place aliasing (#24305) Yash Raj Pandey 2026-06-09 03:24:27 -04:00
  • d76464b2a9 default top_p 0.9 Concedo 2026-06-09 14:29:23 +08:00
  • e3471b3e73 Remove case for GGML_TYPE_Q4_K in mvvq.cu (#23528) ravel7524 2026-06-09 07:46:23 +02:00
  • 3ac3c20c96 ggml-webgpu: Add clang-format job (#24308) Reese Levine 2026-06-08 20:54:24 -07:00
  • 1e1aca09da ggml-webgpu: Improve prefill speeds for k-quants + refactor matmul for Q4/Q5/Q8 and k-quants (#24225) Masashi Yoshimura 2026-06-09 07:19:56 +09:00
  • 7d2b45b4f7 mtp: support for gemma-4 E2B and E4B assistants (#24282) Max Krasnyansky 2026-06-08 13:48:52 -07:00
  • 42a0afd594 server : do not parse when flushing http headers (#24281) Aldehir Rojas 2026-06-08 13:32:41 -05:00
  • a66d50588b graph: guard iswa kq_mask on its own buffer (#24294) Pascal 2026-06-08 19:20:28 +02:00
  • 1705d434f6 [ggml-webgpu] Handle buffer overlap / buffer aliasing for concat operator (#24000) Nikhil Jain 2026-06-08 08:07:31 -07:00
  • 3b3da01dc2 [ggml-webgpu] Implement 2D workgroups for scale, binary, and unary ops (#24044) Nikhil Jain 2026-06-08 08:07:15 -07:00
  • 3ebe862b5d docker: install ffmpeg in the released image (#24302) Xuan-Son Nguyen 2026-06-08 16:59:57 +02:00
  • de03ce6b8a fix cmake Concedo 2026-06-08 21:03:15 +08:00
  • a53b3f7411 sd: sync with master-679-f3fd359 (#2257) Wagner Bruna 2026-06-08 09:42:57 -03:00
  • 8f83d6c271 mtmd : add video input support (#24269) Xuan-Son Nguyen 2026-06-08 13:40:12 +02:00
  • c2b1518fd4 sync : ggml Georgi Gerganov 2026-06-08 12:56:07 +03:00
  • 6a1de6fbf1 ggml : bump version to 0.14.0 (ggml/1533) Georgi Gerganov 2026-06-08 12:51:59 +03:00
  • 715b86a366 cli: fix spinner not show during prompt processing (#24283) Xuan-Son Nguyen 2026-06-08 11:11:45 +02:00
  • c74759a244 vulkan: Use cm2 decode_vector for mul_mat_id B matrix loads (#23991) Jeff Bolz 2026-06-08 03:40:37 -05:00
  • c622a7b96b default temp 0.7 Concedo 2026-06-08 16:34:52 +08:00
  • b5ae1305d4 toggle jinja enables jinjatools Concedo 2026-06-08 16:31:21 +08:00
  • 0f7fada56b cuda: reset cuda context after reading memory size (#23935) Ruben Ortlam 2026-06-08 10:22:44 +02:00
  • 0184f27804 handle anthropic tool responses Concedo 2026-06-08 16:16:22 +08:00
  • d1b5db9109 claude support multimedia content Concedo 2026-06-08 15:33:42 +08:00
  • 21a774a12d anthropic handle thinking Concedo 2026-06-08 14:55:46 +08:00
  • 19bba67c1f HIP: add gfx1152 and gfx1153 to RDNA3.5 (#24129) Harkirat Gill 2026-06-08 02:33:23 -04:00
  • daf6bc9f2d metal : fix im2col 1D case (audio models) (#24220) Xuan-Son Nguyen 2026-06-08 08:03:18 +02:00
  • 8d06b94604 update docs (+1 squashed commits) Concedo 2026-06-08 11:12:14 +08:00
  • d403f00ec3 [SYCL] Update compute runtime version to 26.x in docker (#24070) Neo Zhang 2026-06-08 10:35:18 +08:00
  • 9e3b928fd8 common : relax sampler name matching (#23744) ddh0 2026-06-07 15:48:11 -05:00
  • 8a963fc10e convert : fix conversion for Mistral-Medium-3.5-128B (#24268) David Friehs 2026-06-07 21:41:39 +02:00
  • 379ac6673b kv-cache : avoid kv cells copies (#24277) Georgi Gerganov 2026-06-07 21:42:54 +03:00
  • b7a16b819c still wip for claude tool calling Concedo 2026-06-08 01:26:40 +08:00
  • 52630ad13a wip anthropic tool calling Concedo 2026-06-08 00:58:43 +08:00
  • f0156d1401 kv-cache: follow the source cache size when sharing cells (#24267) Pascal 2026-06-07 17:33:00 +02:00
  • c74af42711 handle anthropic tool calls Concedo 2026-06-07 23:20:42 +08:00
  • da35c69bc4 clean path and strip query params for all http POST routes Concedo 2026-06-07 22:37:00 +08:00
  • c2a41133ea fix makefile for tools Concedo 2026-06-07 22:24:10 +08:00
  • 8f5ef2a927 cmake fix Concedo 2026-06-07 22:19:23 +08:00
  • 635beb6891 sd: sync to master-678-dfb2390 (#2251) Wagner Bruna 2026-06-07 11:18:03 -03:00
  • 17117ecf1d updated lite Concedo 2026-06-07 21:57:02 +08:00
  • 119837c5a1 ssl accept more extensions (+1 squashed commits) Concedo 2026-06-07 21:05:16 +08:00
  • 04eb4c446d llama : add Gemma4 MTP (#23398) Aman Gupta 2026-06-07 20:50:54 +08:00
  • 8a091c47ab spec : fix vocab compatibility check (#24256) Sigbjørn Skjæret 2026-06-07 13:43:52 +02:00
  • e40e5c660e Merge commit '5a69c974392020e514c3b2b2910bb92f847cb4c9' into concedo_experimental Concedo 2026-06-07 17:46:09 +08:00
  • 465b1f0e75 arg: Skip mmproj download when user supplied mmproj (#24239) konradmb 2026-06-07 11:18:44 +02:00
  • 202aaef40b Merge commit '6effcecd0bf3cb2209999cecfa297ed4d8523b5a' into concedo_experimental Concedo 2026-06-07 17:10:58 +08:00
  • 5f39666705 updated lite (+1 squashed commits) Concedo 2026-06-07 16:09:35 +08:00