Public/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-09-19 01:04:55 +02:00
Code Issues Packages Projects Releases Wiki Activity

Commit Graph

  • 549630bae1 feat: render capability icons in the meta row of multi-line model ids Aleksander Grygier 2026-09-01 12:50:55 +02:00
  • 5cbfb9e5b0 feat: request base_model tags so search rows get base org avatars Aleksander Grygier 2026-09-01 12:49:17 +02:00
  • c26ffe3440 feat: mark shared draft variants on the sidecar badge Aleksander Grygier 2026-09-01 12:47:28 +02:00
  • 5079be7fa5 fix: restore componentized download options styling Aleksander Grygier 2026-09-01 12:39:00 +02:00
  • df2ad7e69e refactor: read the catalog from store state in catalogBuilds Aleksander Grygier 2026-09-01 12:16:00 +02:00
  • 6775c200e2 feat: render discover rows from expanded HF list data Aleksander Grygier 2026-09-01 12:15:06 +02:00
  • 7599e2c602 feat: label shared draft variants in download options Aleksander Grygier 2026-09-01 12:14:06 +02:00
  • 1c19021c94 feat: single-line scrollable terminal command in download options Aleksander Grygier 2026-09-01 12:13:26 +02:00
  • 19b3686787 refactor: extract ModelsDiscoverModelDetailsMetadataItem component Aleksander Grygier 2026-09-01 12:13:12 +02:00
  • cb1bc7511c feat: skeleton loading states for model list and details Aleksander Grygier 2026-09-01 12:05:56 +02:00
  • 025e876d1d fix: detect sidecar GGUFs nested in repo folders Aleksander Grygier 2026-09-01 12:05:33 +02:00
  • cdac3a729d feat: WIP Aleksander Grygier 2026-09-01 11:20:34 +02:00
  • 10f985a047 feat: WIP Aleksander Grygier 2026-09-01 10:34:12 +02:00
  • 065e8d883a chore: Add LLAMA-APP-REUSE comments Aleksander Grygier 2026-09-01 08:24:36 +02:00
  • c024c1c567 feat: Models Downloading UI/UX Aleksander Grygier 2026-09-01 08:15:37 +02:00
  • bd1f21efb3 ui : show downloaded quants and drafts as static chips Aleksander Grygier 2026-09-01 01:25:30 +02:00
  • 5ef15ee2ce ui : merge download options and terminal commands into one panel Aleksander Grygier 2026-09-01 00:21:23 +02:00
  • 6be54d7bd6 ui : add download manager pieces and the list search component Aleksander Grygier 2026-08-31 23:20:17 +02:00
  • e436b5e96c ui : restructure discover components to the target names Aleksander Grygier 2026-08-31 23:10:15 +02:00
  • bd2a47e27f ui : add a Discover models trigger to the model selector Aleksander Grygier 2026-08-31 17:24:16 +02:00
  • b5d4ab37c5 ui : wire the discover dialog to live data and downloads Aleksander Grygier 2026-08-31 17:02:12 +02:00
  • 09e47cd45a ui : simplify download options to plain memory estimate Aleksander Grygier 2026-08-31 16:58:33 +02:00
  • 94e20a6059 ui : add models discover components with stories Aleksander Grygier 2026-08-30 18:40:30 +02:00
  • 17731e9a92 ui : mark llama-app-reusable code with a LLAMA-APP-REUSE tag Aleksander Grygier 2026-08-31 17:56:21 +02:00
  • d4482116dd ui : mark llama-app-reusable code with a LLAMA-APP-REUSE tag Aleksander Grygier 2026-08-30 08:38:17 +02:00
  • bac2c2d9eb ui : fix double blank line in model types Aleksander Grygier 2026-08-31 17:30:28 +02:00
  • 6629357df4 ui : add download state tracking to the model status manager Aleksander Grygier 2026-08-31 16:47:51 +02:00
  • fb3e6277d1 ui : add model download pipeline Aleksander Grygier 2026-08-29 12:39:17 +02:00
  • cd24a67c4a ui : simplify model memory estimation Aleksander Grygier 2026-08-31 15:37:27 +02:00
  • bd90ba5d7a ui : add model compatibility estimation Aleksander Grygier 2026-08-29 12:32:23 +02:00
  • 41d3821e0d ui : move catalog url to models-discover constants Aleksander Grygier 2026-08-29 13:25:04 +02:00
  • da017bcb53 ui : move HF constants to constants and enums modules Aleksander Grygier 2026-08-29 12:57:08 +02:00
  • 8d496326f7 ui : follow MODEL_ID regex rename in huggingface service Aleksander Grygier 2026-08-29 11:54:18 +02:00
  • 0871357fe6 ui : add huggingface hub data layer Aleksander Grygier 2026-08-29 11:22:41 +02:00
  • ad8e42f71a ui : lowercase reasoning capability and use sidecar enums in tests Aleksander Grygier 2026-08-29 12:05:31 +02:00
  • bb44a904a4 ui : address review on model id parsing Aleksander Grygier 2026-08-29 11:53:56 +02:00
  • 2bf5c2c837 ui : parse sidecar types in model ids Aleksander Grygier 2026-08-28 13:40:58 +02:00
  • 693f870034 ui : add format:files script for formatting changed files only Aleksander Grygier 2026-08-28 11:03:57 +02:00
  • 01da32baf2 ui : rename model API types to mirror endpoints Aleksander Grygier 2026-08-28 11:03:49 +02:00
  • 2d64ea1290 ui : remove dead ChatFormActionAddMcpSubmenu component Aleksander Grygier 2026-08-28 11:03:40 +02:00
  • 85d5703a3b ui : fix MCP image attachments not displayed in tool block (#25789) (#28089) nachobh 2026-09-04 19:53:16 +02:00
  • 1548a240e3 opencl: extend the elementwise and data‐movement op coverage (#27633) b10814 Hongqiang Wang 2026-09-04 10:12:26 -07:00
  • 4acf4a4cb8 opencl: add Adreno xmem SDPA path (#26331) b10813 yzyyzyhhh 2026-09-05 01:12:05 +08:00
  • cef6c528f8 Materialize input_scales also for FP8 when converting osimons/ocp_fp8 Oliver Simons 2026-09-04 18:41:24 +02:00
  • adb9affc96 Fix python type-checker Oliver Simons 2026-08-31 15:23:26 +02:00
  • dd53768baf WIP OCP FP8 E4M3 support Oliver Simons 2026-08-21 18:38:22 +02:00
  • b6cc43272d metal : fix memory leak in early return nikwen/metal-leak Niklas Wenzel 2026-09-04 18:33:10 +02:00
  • 8b4b3558f1 ci : move more jobs to ccache-buckets (#28375) Sigbjørn Skjæret 2026-09-04 15:50:33 +02:00
  • 7c2e0dea43 common : enable default speculative config gg/spec-default-by-default Georgi Gerganov 2026-09-04 10:59:53 +03:00
  • 1863ac0333 ui: export conversations from database instead of cached store (#27432) Tom Tan 2026-09-04 06:13:10 -07:00
  • 49c0dc82b8 model : add Tencent Hy 4 (hy_v4) preview architecture support (#28127) HongHuang 2026-09-04 20:31:36 +08:00
  • 477ecf18ef spec: single device drafter should create meta backend wrapper Aman Gupta 2026-09-04 20:28:56 +08:00
  • 5266f24da7 llama.cpp : bump version to 0.4.0 (#28386) v0.4.0 b10809 Georgi Gerganov 2026-09-04 15:22:38 +03:00
  • 64a155d242 sync : ggml (#28379) Georgi Gerganov 2026-09-04 14:39:19 +03:00
  • 163a40796f model, mtmd: fix gemma4 vision handling (#28335) Xuan-Son Nguyen 2026-09-04 12:23:27 +02:00
  • 8f83678fd8 metal : add remaining fa-vec tunings for M3 Max (#28373) Niklas Wenzel 2026-09-04 11:46:31 +02:00
  • 86b351fd64 ggml : replace compile definitions with version.h.in (#28364) Daniel Bevenius 2026-09-04 10:28:23 +02:00
  • d509cb1e86 Don't use npx inside a package.json script (#28270) Evan Huus 2026-09-04 04:27:56 -04:00
  • 4cbe8b070b ggml : don't crash when backend search path can't be read (#28271) Adrien Gallouët 2026-09-04 09:24:06 +02:00
  • 24f5bf8a41 ggml : remove GGML_CUDA_PEER_MAX_BATCH_SIZE (#28177) Adrien Gallouët 2026-09-04 09:22:01 +02:00
  • a529af96e2 docs : update maintainer PRs link and regenerate AUTHORS (#28365) Georgi Gerganov 2026-09-04 10:20:49 +03:00
  • 38521ec33f vendor: update BoringSSL to 0.20260903.0 (#28354) Alessandro de Oliveira Faria (A.K.A.CABELO) 2026-09-04 04:10:26 -03:00
  • 0ef4d560e1 ci : disable failing openvino tests (#28347) Ravi Panchumarthy 2026-09-03 23:18:11 -07:00
  • c390d0abbc common : make build info output stream configurable (#28322) b10798 Adrien Gallouët 2026-09-04 08:13:20 +02:00
  • 832fd6f174 ggml-cpu(s390x) : fix q5_1 uninitialized v_acc (#28332) b10797 Aaron Teo 2026-09-04 13:55:50 +08:00
  • 9a4843cf2f src : add n_expert_used_max function (#28323) b10796 Daniel Bevenius 2026-09-04 06:36:51 +02:00
  • 6703d7894c sycl: fuse rms_norm+mul+add and add+add residual chains (#27610) b10795 Frosty40 2026-09-03 23:05:40 -05:00
  • f9f09f02cc SYCL: Refactor GGML_SYCL_ENABLE_MKL_FA to global var (#26863) b10794 Ozymandias_EBON 2026-09-03 21:45:53 -05:00
  • 19f255903c add check script xsn/synthid Xuan Son Nguyen 2026-09-04 01:17:09 +02:00
  • 8b46bb9640 add --synthid-keys Xuan Son Nguyen 2026-09-04 01:09:05 +02:00
  • 73c900a97d add synthid sampler Xuan Son Nguyen 2026-09-04 01:01:45 +02:00
  • d230ddd763 llama: fix whole source code rebuilt on each new commit (#28278) b10793 Xuan-Son Nguyen 2026-09-03 23:53:04 +02:00
  • c5a5535e6e common/json-schema : fix GBNF grammar generation for empty object schemas (#28279) b10792 Sergey Sklyarov 2026-09-03 22:37:50 +02:00
  • 95ef7fc160 opencl: quant lm_head / decode GEMV and medium-batch GEMM optimizations (speculative decoding/MTP) (#26477) b10791 Hongqiang Wang 2026-09-03 09:46:19 -07:00
  • 8c1a25166b tune MMVQ to MMQ crossover for SM87 (#28285) b10790 kbenkhaled 2026-09-03 12:40:42 -04:00
  • d30500b83b snapdragon: ci updates to use new run script (#28293) Max Krasnyansky 2026-09-03 08:59:11 -07:00
  • e107984bcf ops: add Hexagon to ops.md and update main README.md (#28263) Todor Boinovski 2026-09-03 07:14:36 -07:00
  • 42f0225fea server : use pytest-xdist for server tests (#28298) Daniel Bevenius 2026-09-03 15:04:30 +02:00
  • de8656bd94 mtmd: propagate const to preproc class (#28310) b10786 Xuan-Son Nguyen 2026-09-03 12:57:10 +02:00
  • 7bb0fc18f6 metal : add sparse FA (#28098) b10785 Georgi Gerganov 2026-09-03 13:51:13 +03:00
  • 0df017d6dd metal : fix glu dispatch with ne00 = 1 (#28306) b10784 Georgi Gerganov 2026-09-03 13:25:41 +03:00
  • 3623b0ae48 mtmd: propagate const to preproc class xsn/mtmd_more_const Xuan Son Nguyen 2026-09-03 12:15:22 +02:00
  • f45576aa86 mtmd : add const in various places (#28307) b10783 Mads Marquart 2026-09-03 12:12:49 +02:00
  • 0ba6499c3b CUDA: Allow concurrent streams per split for multi-GPU (#28198) b10782 Tanner Bruhn 2026-09-03 12:03:03 +02:00
  • c7bda030e7 vulkan: fix FA dequant path engagement (#28190) b10781 Nathan Wilson 2026-09-03 15:40:34 +07:00
  • a2ec6b0fff server: do not advertise a connect code without the tunnel xsn/llama-connect Pascal 2026-09-03 10:12:11 +02:00
  • 0df974d777 sycl : enhance the api to support peer-to-peer copy (#27550) b10780 Neo Zhang 2026-09-03 15:41:07 +08:00
  • d646c9d155 convert : skip bias_vl tensor in DeepSeek-V4 DSpark conversion (#28294) Georgi Gerganov 2026-09-03 10:37:23 +03:00
  • 5ec4eab69e misc : prevent RAM peaking at model loading stage (#27483) b10778 Tarek Dakhran 2026-09-03 09:32:24 +02:00
  • 4aa6ffba25 sycl: reduce redundant work in Q4_K multi-column MMVQ (#27062) b10777 Eurekatic 2026-09-03 08:59:06 +02:00
  • c61b98b875 model: add NVIDIA Nemotron-3-Puzzle-75B-A9B (NemotronHPuzzle) support (#25444) b10776 Yaniss Amazouz 2026-09-03 09:53:08 +03:00
  • ea14703b86 llama: fix whole source code rebuilt on each new commit xsn/fix_rebuild_new_commit Xuan Son Nguyen 2026-09-03 01:07:06 +02:00
  • 67a17c17ca mtmd: fix idefics3 preproc (#28273) b10775 Xuan-Son Nguyen 2026-09-03 01:00:57 +02:00
  • a75348a2ae fix windows build Xuan Son Nguyen 2026-09-03 00:59:39 +02:00
  • 339444c12a nits Xuan Son Nguyen 2026-09-03 00:50:00 +02:00
  • e9df25130c add props.connect_code Xuan Son Nguyen 2026-09-03 00:44:11 +02:00
  • a6cf7b8f18 make it clear that it's experimental Xuan Son Nguyen 2026-09-03 00:29:12 +02:00
  • a3f62cc133 wire it up Xuan Son Nguyen 2026-09-03 00:22:15 +02:00
  • 0349b3fbcb mtmd: fix idefics3 preproc xsn/idefics_fix Xuan Son Nguyen 2026-09-02 23:56:21 +02:00
  • 159b741427 finetune: fix no KV cache (#27199) b10774 Xuan-Son Nguyen 2026-09-02 23:53:32 +02:00