Public/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-09-19 09:15:04 +02:00
Code Issues Packages Projects Releases Wiki Activity

Commit Graph

  • 2fab2f41b2 ui : move model list into a submenu within the model selector Aleksander Grygier 2026-08-15 22:53:56 +02:00
  • 4d6874bbda ui : add show-org-name-in-trigger display setting Aleksander Grygier 2026-08-15 22:53:48 +02:00
  • 3d0da6f4eb ui : keep reasoning submenu visible regardless of model state Aleksander Grygier 2026-08-15 22:53:26 +02:00
  • 2190337d6c ui : show reasoning and modality icons on model options and search by modality Aleksander Grygier 2026-08-15 22:53:18 +02:00
  • 7c8ece9a3a ui : strip trailing container-format segments from parsed model names Aleksander Grygier 2026-08-15 22:53:04 +02:00
  • f1357e4998 ui: ESLint config updates (#27700) Aleksander Grygier 2026-08-25 14:34:34 +02:00
  • 3737e41370 metal : null-check buffer alloc to fix OOM crash (#25371) b10622 Yuri Khrustalev 2026-08-25 07:35:39 -04:00
  • af2146b768 allow dmabuf p2p 0cc4m/vulkan-allreduce Ruben Ortlam 2026-08-25 13:08:16 +02:00
  • b4acc6d3d6 fix compile issue Ruben Ortlam 2026-08-25 12:33:50 +02:00
  • 6634f71f4a Merge branch 'pr-25051' into 0cc4m/vulkan-allreduce Ruben Ortlam 2026-08-25 12:26:42 +02:00
  • e46b3ae5ff reverse check order 0cc4m/vulkan-d2d-copy Ruben Ortlam 2026-08-25 12:19:26 +02:00
  • 562b5573a9 fix compile issues 0cc4m/vulkan-device-cpy-benchmark Ruben Ortlam 2026-08-25 12:04:13 +02:00
  • 22be677365 check once Ruben Ortlam 2026-06-29 16:03:26 +02:00
  • b72b4e592c fix cleanup Ruben Ortlam 2026-06-29 15:45:12 +02:00
  • 76c4417827 add dmabuf capability check Ruben Ortlam 2026-06-29 13:51:47 +02:00
  • 7d3f70332e add reverse order tests for dmabuf Ruben Ortlam 2026-05-21 14:44:52 +02:00
  • d49112ceab skip dmabuf_p2p when one device is nvidia, due to driver crashes Ruben Ortlam 2026-05-21 14:01:49 +02:00
  • 5e9b414113 improve output device consistency Ruben Ortlam 2026-05-21 13:54:12 +02:00
  • 4b35cf88aa catch driver issues in benchmarks Ruben Ortlam 2026-05-21 13:35:39 +02:00
  • f08f1cad46 add host dmabuf p2p test Ruben Ortlam 2026-05-21 13:16:37 +02:00
  • b39d8bfa05 output device group info Ruben Ortlam 2026-05-01 14:53:12 +02:00
  • 1e9c9bd131 add device group test Ruben Ortlam 2026-05-01 07:49:49 +02:00
  • e1b0bd7ab8 clean up tests, add dma_buf test Ruben Ortlam 2026-04-29 15:20:42 +02:00
  • efdc1cae42 benchmark Ruben Ortlam 2026-04-08 18:26:50 +02:00
  • 50e0a2dd81 fix compile issues Ruben Ortlam 2026-08-25 11:48:52 +02:00
  • c1d0e7a004 llama.cpp : bump version to 0.3.0 (#27696) v0.3.0 b10621 Georgi Gerganov 2026-08-25 12:42:21 +03:00
  • 4d879b9cfa use memcpy for small copies across host-visible memory Ruben Ortlam 2026-06-18 11:55:10 +02:00
  • bce45fbe90 add semi-async staging copy and use it over syncfd for small copies Ruben Ortlam 2026-06-11 11:37:09 +02:00
  • bac1369095 swap dmabuf check order Ruben Ortlam 2026-06-10 15:00:00 +02:00
  • 86ad441765 use allocator instead of hop2 Ruben Ortlam 2026-05-29 15:08:39 +02:00
  • 5f512ae71b use sync_fd binary semaphores for cross-driver synchronization Ruben Ortlam 2026-05-26 09:33:34 +02:00
  • 4f4cea3112 double buffering Ruben Ortlam 2026-05-26 08:05:14 +02:00
  • 3e53e38de3 fixes, disable semaphore sharing on Nvidia + non-Nvidia Ruben Ortlam 2026-05-26 07:37:24 +02:00
  • bf316ac516 add async copy Ruben Ortlam 2026-05-25 16:27:17 +02:00
  • 740c12733e vulkan: add optimized device to device copy function Ruben Ortlam 2026-05-25 16:03:44 +02:00
  • 81191affa5 sync : ggml b10620 Georgi Gerganov 2026-08-25 11:46:33 +03:00
  • 93882361f1 ggml : bump version to 0.22.0 (ggml/1607) Georgi Gerganov 2026-08-25 11:27:17 +03:00
  • eb25b7263e grammar : parse \- in char classes as literal hyphen (#27591) b10618 Saad Ali 2026-08-25 11:05:24 +05:00
  • 814d84bc9d sycl : mark tq2_0 as not supported (#27660) b10617 Neo Zhang 2026-08-25 14:04:58 +08:00
  • 5ea87ddad2 webgpu : fix handling of infinity values during ARGSORT and TOP_K (#27538) fairydreaming 2026-08-25 07:08:06 +02:00
  • f280b26983 metal : per-device tuned (Q, NE) for flash-attn vec (#26570) b10615 YiChen Lv 2026-08-25 00:22:27 +08:00
  • b615f5b4bd metal: per-op source split + parallel compile (#26561) b10614 YiChen Lv 2026-08-25 00:16:13 +08:00
  • b3c3b96a13 misc : read repetition_penalty from generation_config.json (#27659) Tarek Dakhran 2026-08-24 16:01:35 +02:00
  • 7584430716 tests : disable DOTS3NOTE arch test for WebGPU (#27654) b10612 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) b10610 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) b10608 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) b10606 Georgi Gerganov 2026-08-24 10:43:04 +03:00
  • a130532ae1 mamba2 : Flatten in/out projections to dispatch GEMM instead of GEMV (#27513) b10605 Prabhsimran Singh 2026-08-24 11:55:11 +05:30
  • bf0a29cc16 Deepseek 4: -sm tensor (#26490) b10604 Aman Gupta 2026-08-24 11:50:25 +05:30
  • 8e8ae2effa windows: handle broken pipe case xsn/mtmd_moov Xuan Son Nguyen 2026-08-24 01:08:26 +02:00
  • c060ca974c model : support MTP in GLM-4.5-Air (#26534) b10603 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) b10599 Xuan-Son Nguyen 2026-08-23 18:38:51 +02:00
  • 56db501e73 mtmd: use pillow-accurate algo, correct resize_algo for all models (#27594) b10598 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) b10595 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) b10594 Bartosz Taudul 2026-08-23 14:39:16 +02:00
  • b0539c43ed DeepseekV4: fix rollback with multi-seq (#26756) b10593 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
  • 1aef9f04cc speed optimization xsn/mtmd_pillow Xuan Son Nguyen 2026-08-23 12:39:39 +02:00
  • c2a71e66a5 fix SIGPIPE Xuan Son Nguyen 2026-08-23 12:13:35 +02:00
  • 25d92d9135 mtmd: use pillow-accurate resize algo, correct resize_algo for all models Xuan Son Nguyen 2026-08-23 12:00:13 +02:00
  • ba8b1c440d mtmd: video: fix moov at the end of file Xuan Son Nguyen 2026-08-23 11:37:50 +02:00
  • 8144f3192e ui: Chat Conversation Tabbed navigation (#27263) Aleksander Grygier 2026-08-23 10:46:49 +02:00
  • 6657ded4fa vendor : update subprocess.h (#27409) b10590 Alessandro de Oliveira Faria (A.K.A.CABELO) 2026-08-23 04:38:29 -03:00
  • 29ea9412a6 cuda : add POOL_1D support (#27573) b10589 Aman Karki 2026-08-23 13:07:32 +05:30
  • 70adb1b4ce common: json.h: fix clang lto (#27575) b10588 Xuan-Son Nguyen 2026-08-23 01:11:10 +02:00
  • 4fbd8a615b common: json.h: fix clang lto xsn/common_json_lto Xuan Son Nguyen 2026-08-22 23:44:05 +02:00
  • 3f545becce vulkan : added the PAD_REFLECT_1D operation (#26586) b10587 Safi Ullah 2026-08-23 00:42:20 +05:00
  • f2af870515 test: move tools/parser to tests xsn/tool_parser_test Xuan Son Nguyen 2026-08-22 17:31:03 +02:00
  • b21e4de745 mtmd: use ggml_rope_set_offset (#27521) b10586 Xuan-Son Nguyen 2026-08-22 16:33:47 +02:00
  • 79a9d8501d add comment xsn/ggml_rope_off_mtmd Xuan Son Nguyen 2026-08-22 16:33:13 +02:00
  • d9f918d2d0 common: add json.h abstraction (#27511) b10585 Xuan-Son Nguyen 2026-08-22 16:28:28 +02:00
  • 2fb989b9e7 fit: also take into account n_streams (#27496) b10584 Xuan-Son Nguyen 2026-08-22 16:16:06 +02:00
  • aeae9626e7 Merge branch 'master' into xsn/common_json xsn/common_json Xuan Son Nguyen 2026-08-22 15:55:07 +02:00
  • 9fee29e943 arg: remove -no-cnv from cli [no ci] (#27542) Xuan-Son Nguyen 2026-08-22 15:53:56 +02:00
  • 2e3dedc13e clarify about not adding exccesive test cases xsn/rm_no_cnv_cli Xuan Son Nguyen 2026-08-22 15:51:31 +02:00
  • dcb0eb7c5a arg: remove -no-cnv from cli Xuan Son Nguyen 2026-08-22 15:37:38 +02:00
  • ff0b1959a4 rm redundant decl Xuan Son Nguyen 2026-08-22 15:22:57 +02:00
  • 3c7135fc4d add some comments Xuan Son Nguyen 2026-08-22 15:20:35 +02:00
  • e85caa81ea ci : Restore ROCm job for Ubuntu (#27399) b10582 Mario Limonciello 2026-08-22 05:28:30 -05:00
  • 2115b73d8e model : support DSpark for bailingmoe3 (#27508) b10581 Tiwei Bie 2026-08-22 17:19:48 +08:00
  • 54ee5ee643 mtmd: support dots3-note vision+audio (#27524) b10580 Xuan-Son Nguyen 2026-08-22 10:35:50 +02:00
  • 527b42a575 rm json-shim Xuan Son Nguyen 2026-08-22 10:35:31 +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) b10578 Kartik Sirohi 2026-08-22 14:00:31 +05:30
  • ad32502d14 clean up Xuan Son Nguyen 2026-08-22 10:28:04 +02:00
  • ddffcee550 Update gguf-py/gguf/tensor_mapping.py xsn/dots3-note-mtmd Xuan-Son Nguyen 2026-08-22 10:09:51 +02:00
  • b89d589040 harden a bit Xuan Son Nguyen 2026-08-22 10:08:39 +02:00
  • 2c6b141efb common : fix draft-mtp with embeddings (#26352, #27299) (#27400) b10577 Shahir BIn Zulfiker 2026-08-22 13:44:22 +06:00
  • 8672290039 sycl : add Q2_K reordered MMVQ and ESIMD kernels (again) (#27490) b10576 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
  • 3f38c9d225 Merge remote-tracking branch 'origin/master' into xsn/dots3-note-mtmd Xuan Son Nguyen 2026-08-22 02:15:52 +02:00