Public/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-09-19 17:24:57 +02:00
Code Issues Packages Projects Releases Wiki Activity

Commit Graph

  • f370471abf adapt to upstream changes 0cc4m/server-memory-limit Ruben Ortlam 2026-08-11 14:00:58 +02:00
  • eac4c8b76c server: add --models-memory-max parameter to allow dynamically unloading models when they exceed a memory size threshold Ruben Ortlam 2026-03-29 10:00:49 +02:00
  • 8d274dd7c6 ui: fix context gauge for single-model usage (#25738) Tom Tan 2026-08-11 04:42:48 -07:00
  • 704485942a ci: hip-quality-check: update vgpr spill ignore list (#26859) uvos 2026-08-11 11:47:57 +02:00
  • 1138b851fa model-conversion : use save_output_data for causual embeddings [no ci] (#26890) Daniel Bevenius 2026-08-11 11:41:38 +02:00
  • 9afff1b748 tests : fix running server tests on windows (#26889) Georgi Gerganov 2026-08-11 12:07:15 +03:00
  • 153d324bcf llama: add default load-mode auto, which avoids mmap on iGPUs (#26081) Ruben Ortlam 2026-08-11 08:20:46 +02:00
  • b3df57286c tests : clean-up server test, use tests.sh in ci (#26886) Georgi Gerganov 2026-08-11 09:07:13 +03:00
  • 4801e3c567 tests : disable backend sampler hip multi output (#26878) b10362 Jim Wu 2026-08-10 21:21:32 -07:00
  • 14e78ddef7 model : fix SWA not being enabled for EXAONE 4.5 (#26848) b10361 Junmo Kim 2026-08-11 13:20:17 +09:00
  • 48d22e295e common/peg : suppress incomplete escape sequences (#26780) b10360 Aldehir Rojas 2026-08-10 23:10:31 -05:00
  • 84f7129467 ggml-webgpu: fix CI errors from #25025 and #25262 (#26566) b10359 Masashi Yoshimura 2026-08-11 13:10:00 +09:00
  • f236e272f0 rm gen_flow_temp xsn/pocket-tts Xuan Son Nguyen 2026-08-11 01:01:16 +02:00
  • 606375f8c3 add docs Xuan Son Nguyen 2026-08-11 00:56:18 +02:00
  • 1d591cc2b7 add mtmd_gen_inp_default Xuan Son Nguyen 2026-08-11 00:51:10 +02:00
  • 3e47aaec49 lint Xuan Son Nguyen 2026-08-11 00:26:53 +02:00
  • 93055059cc less invasive base.py Xuan Son Nguyen 2026-08-11 00:19:14 +02:00
  • 6c197a77ea address security problems Xuan Son Nguyen 2026-08-10 23:54:13 +02:00
  • 030ebb558a Address review comment of PR 25532 (#26852) b10358 Gaurav Garg 2026-08-11 00:02:25 +05:30
  • 689e227db4 opencl: transpose the K tile in local memory for FA prefill kernels (#26428) b10357 Hongqiang Wang 2026-08-10 11:09:19 -07:00
  • 0666ad2b2b ci : target ROCm 7.14 for build and release (#25775) b10356 Mario Limonciello 2026-08-10 12:53:12 -05:00
  • 57dc111688 update docs Xuan Son Nguyen 2026-08-10 19:39:22 +02:00
  • 739aee5643 Merge branch 'master' into xsn/pocket-tts Xuan Son Nguyen 2026-08-10 19:18:09 +02:00
  • dd1ea52433 llama : support multi-output backend sampling (#25532) b10355 Gaurav Garg 2026-08-10 19:28:56 +05:30
  • d2f83055d6 ggml-cpu : fix CPU affinity mask being ignored on Android (#26838) b10354 Hitesh Chopra 2026-08-10 17:43:40 +05:30
  • f8def7fe16 ggml : require contiguous src for ROLL on CUDA and Metal (#25928) b10353 Yash Raj Pandey 2026-08-10 08:01:44 -04:00
  • 4dee52f82d ui: UI/chat form follow ups (#26743) Pascal 2026-08-10 13:32:51 +02:00
  • e5275f6f77 ci : don't specify python version in server-sanitize for broader runner compatibility (#26840) Sigbjørn Skjæret 2026-08-10 13:32:22 +02:00
  • 4ae84dea27 server: add more tool isolation support (ssh remote + podman rootless) (#26774) Pascal 2026-08-10 13:31:09 +02:00
  • 62bf73d25c model: Muse Glimmer Support (#26841) Pedro Cuenca 2026-08-10 13:07:27 +02:00
  • a52077c4ca chat : Align Laguna-S-2.1 chat template to huggingface (#26232) Guido Imperiale 2026-08-10 11:20:59 +01:00
  • 4c6766fd7e vendor: sync subprocess.h and drop local patches (#26808) Pascal 2026-08-10 11:59:08 +02:00
  • 86c298fb8a llama: Restore quantization of mmprojs (#26818) Pedro Cuenca 2026-08-10 11:58:32 +02:00
  • 2e2d99cfd2 ci: Add support for CUDA 13.4 ARM64 builds for Windows (#26650) shivamkumard-ctrl 2026-08-10 14:16:44 +05:30
  • 7a20b417f4 model: add MTP support for Nemotron model (#26725) b10344 Ruixiang Wang 2026-08-10 10:25:24 +02:00
  • e23e9440eb vendor : update cpp-httplib to 0.53.0 (#26821) b10343 Alessandro de Oliveira Faria (A.K.A.CABELO) 2026-08-10 04:57:45 -03:00
  • 157b81fe6d model : Granite-Switch Architecture (#25107) b10342 Bar Haim 2026-08-10 00:53:46 -07:00
  • 6ad4ab0ea0 readme : remove dev branches (#26832) Georgi Gerganov 2026-08-10 09:53:26 +03:00
  • 92d1bb0c99 ui: Linting & Formatting scripts (#26819) Aleksander Grygier 2026-08-10 08:38:37 +02:00
  • 1e396e72a8 server: gate the docker tools runtime tests on a real container run (#26826) Pascal 2026-08-10 08:32:58 +02:00
  • 0377426cef model-saver : fix expert shared/chunk FFN length key clobber (#26693) b10338 Caleb DeLeeuw 2026-08-09 23:32:01 -07:00
  • aea252fb4a ci: fix the ctest sanitize runs (#26593) Eve 2026-08-10 06:31:28 +00:00
  • f401bb1390 ggml-webgpu : refactor several wgsl files and simplify flash_attn wgsl. (#26134) b10336 Masashi Yoshimura 2026-08-10 15:29:41 +09:00
  • 74ce15741b ui: degrade the working directory picker when file search is off (#26811) b10335 Pascal 2026-08-09 21:20:23 +02:00
  • 936918514c ci: add pr-draft-label (#26801) Xuan-Son Nguyen 2026-08-09 16:51:21 +02:00
  • 35d6100372 ci: add pr-draft-label xsn/pr-draft-label Xuan Son Nguyen 2026-08-09 13:50:12 +02:00
  • 08659901c4 ggml-cpu : fix missing Q5_0 dispatch in SpaceMiT backend (#26792) b10333 Hao-Chen2337 2026-08-09 18:16:53 +08:00
  • 61141f1487 ci: rm GGML_HIP_ROCWMMA_FATTN (#26760) b10332 Aaron Teo 2026-08-09 18:15:28 +08:00
  • 7ba604f1cb server: report the isolate working directory from get_info (#26773) b10331 Pascal 2026-08-09 00:42:50 +02:00
  • 687e778927 CUDA: fuse rms_norm + mul + rope (+ view + set_rows) (#26767) b10330 Rafail Giavrimis 2026-08-08 17:32:37 +01:00
  • 18f7ad7fc9 server, ui: only offer a working directory when a tool reads it (#26762) b10329 Pascal 2026-08-08 16:36:21 +02:00
  • dd2c7c4471 server: add initial tool isolation support (via docker) (#26507) b10328 Xuan-Son Nguyen 2026-08-08 16:35:53 +02:00
  • 69bf643791 CUDA: fix thread/block count in quantized cpy kernel launches (#26731) b10327 Rafail Giavrimis 2026-08-08 05:40:04 +01:00
  • d483b9b3aa x-tool-docker --> x-tool-runtime xsn/server_docker_isolate Xuan Son Nguyen 2026-08-08 01:48:51 +02:00
  • fdb0107f11 rename sandbox --> isolate Xuan Son Nguyen 2026-08-08 01:41:55 +02:00
  • 9bbb9d023e separate tools_io_sandbox / tools_io_docker Xuan Son Nguyen 2026-08-08 01:40:17 +02:00
  • 0b8c616dd0 cont Xuan Son Nguyen 2026-08-08 01:27:46 +02:00
  • 327c7b9c81 Merge remote-tracking branch 'upstream/master' into xsn/server_docker_isolate Pascal 2026-08-07 23:58:33 +02:00
  • 3653e6d6d5 tts: account for the vocoder pass in the timings line (#26733) b10326 Pascal 2026-08-07 22:35:52 +02:00
  • ae86645c28 Consistify polling frequency of llama-bench with args osimons/llama_bench_poll_update Oliver Simons 2026-08-07 20:59:36 +02:00
  • fc6545d322 allozaur/feat/chat form contenteditable (#26717) Aleksander Grygier 2026-08-07 20:40:10 +02:00
  • 1621a3d388 tests : speed-up server test suite 3x (#26734) Georgi Gerganov 2026-08-07 21:38:32 +03:00
  • 6de1b63473 allozaur/feat/chat slash commands (#26716) Aleksander Grygier 2026-08-07 20:20:01 +02:00
  • f8e30266d2 sycl: coalesce the ssm_conv window loads (#26612) b10322 Titaniumtown 2026-08-07 11:09:32 -07:00
  • a194a75b7e metal : fix NORM/RMS_NORM for row lengths that leave a partial simdgroup (#26708) b10321 robertomeroni 2026-08-07 20:09:07 +02:00
  • 23634783c5 ui: Filesystem @mentions for Chat Form (#26715) Aleksander Grygier 2026-08-07 18:45:54 +02:00
  • 4cb22cd537 mtmd: fix longest_edge ignoring min/max pixels (#26638) b10319 Xuan-Son Nguyen 2026-08-07 18:05:15 +02:00
  • 4cf5cab65d sync : ggml b10318 Georgi Gerganov 2026-08-07 17:10:39 +03:00
  • 933f46f3cb ggml : bump version to 0.19.0 (ggml/1581) Georgi Gerganov 2026-08-07 17:10:01 +03:00
  • 9ba73fd1f5 server : clarify comment in eval_llama_cmpl_schema [no ci] [no release] (#26720) Daniel Bevenius 2026-08-07 15:39:33 +02:00
  • b8b8738f92 Merge branch 'master' into xsn/fix_longest_edge_with_limit xsn/fix_longest_edge_with_limit Xuan Son Nguyen 2026-08-07 15:38:55 +02:00
  • 7e1370694f nits Xuan Son Nguyen 2026-08-07 15:38:49 +02:00
  • f4f7758cae webui: load the model selected via ?model= when ?load=true (#26707) Emanuil Rusev 2026-08-07 16:31:40 +03:00
  • 34e9ee57f5 ui: set npm min-release-age to protect against supply-chain attacks (#26711) Niklas Wenzel 2026-08-07 14:53:51 +02:00
  • dff15d4ac9 server: (router) add LRU scheduler (#26572) b10313 Xuan-Son Nguyen 2026-08-07 14:46:53 +02:00
  • fbb29b3f98 address review comments xsn/server_lru_sched Xuan Son Nguyen 2026-08-07 14:36:59 +02:00
  • 3954a9c39b fix stream case Xuan Son Nguyen 2026-08-04 17:54:18 +02:00
  • 07491664e2 add tests Xuan Son Nguyen 2026-08-04 14:49:31 +02:00
  • 3bf32c0a9b handle coalescing (req leaves waiting queue) Xuan Son Nguyen 2026-08-04 14:31:55 +02:00
  • 02f5052fae add lru_sched Xuan Son Nguyen 2026-08-04 14:11:30 +02:00
  • e1470ee6a2 server: (router) do not evict busy models (#26567) b10312 Xuan-Son Nguyen 2026-08-07 14:39:59 +02:00
  • 1621aade61 server: (router) do not evict busy models xsn/server_ref_count Xuan Son Nguyen 2026-08-04 12:38:54 +02:00
  • 217df17ac3 mtmd: stop feeding the text stream again during Qwen3-TTS generation (#26706) b10311 Pascal 2026-08-07 13:32:52 +02:00
  • cb26014d96 ggml : add aarch64 HWCAP fallbacks and fix fp16 variant detection (#25554) b10310 Kilian Hu 2026-08-07 13:07:10 +02:00
  • 82bb48500a ui: read model modalities from the router model list (#26709) Pascal 2026-08-07 12:07:58 +02:00
  • 42e98813e4 Mitigate crashing issue on Windows MSYS2 UCRT64 environment (GCC 16.1.0) (#26555) b10308 Masato Nakasaka 2026-08-07 02:17:16 -07:00
  • fc3f10b389 sycl: fix UE4M3 parsing (#25608) b10307 Chris Lee 2026-08-06 23:28:53 -06:00
  • 6b5c2efb4e sycl: *glu flat path (#26354) b10306 Titaniumtown 2026-08-06 22:24:40 -07:00
  • 31558dbb76 sycl : Support DSv4 OPs: LIGHTNING_INDEXER,DSV4_HC_COMB,DSV4_HC_POST,DSV4_HC_PRE (#26568) b10305 Neo Zhang 2026-08-07 13:22:23 +08:00
  • c1f4109898 sycl : update guide Q&A and script for device setting (#26442) Neo Zhang 2026-08-07 13:18:47 +08:00
  • eef5f3e343 sycl : fix error Error OP FLASH_ATTN_EXT on arc770 (#26441) b10303 Neo Zhang 2026-08-07 13:17:56 +08:00
  • c074cb3f76 sycl : enhance OP set_rows to support all missed data types (#26515) Neo Zhang 2026-08-07 12:52:52 +08:00
  • 5b87ed30f8 cuda: fix warnings for unused variable/function (#26688) b10301 David Friehs 2026-08-07 06:51:56 +02:00
  • d8d9887228 ci: abort if build requirements are missing (#26368) Niklas Wenzel 2026-08-07 06:50:48 +02:00
  • e40bf88642 metal : avoid threadgroup matrix array instantiation in kernel_lightning_indexer (#26646) b10299 JamePeng 2026-08-07 12:49:14 +08:00
  • 15586e2d71 mtmd: add chunk save/load function (#26645) b10298 Xuan-Son Nguyen 2026-08-06 19:46:40 +02:00
  • 4eef4072b2 nit: drop the dead flow_temp hparam, the pack table holds the default Pascal 2026-08-06 17:06:05 +02:00
  • a73f458f3b clean up code comments Xuan Son Nguyen 2026-08-06 16:42:25 +02:00
  • 4b9a4df9b9 clip.gen.audio.model_variant Xuan Son Nguyen 2026-08-06 16:19:09 +02:00
  • 6a32c29a74 server: fix empty response for /cors-proxy (#26656) b10297 Xuan-Son Nguyen 2026-08-06 15:07:22 +02:00