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

  • 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
  • 15eeceabcb void conflict with boringssl xsn/vendor_hash_mtmd Xuan Son Nguyen 2026-08-17 20:02:56 +02:00
  • b75ecd1971 mtmd : skip thumbnail for non-tiled LFM2 images (#27246) Tarek Dakhran 2026-08-17 19:41:32 +02:00
  • 363b198ad4 server: save processed mtmd chunks as placeholder xsn/server_use_mtmd_placeholder Xuan Son Nguyen 2026-08-17 19:39:51 +02:00
  • 60eeeb6082 cuda : skip UMA override for HIP builds (#27083) b10472 Mario Limonciello 2026-08-17 11:35:36 -05:00
  • 9ae5bba0fe mtmd: use sha256 for input hashing Xuan Son Nguyen 2026-08-17 15:53:04 +02:00
  • 39be55c97e vendor: move hash to vendor (#27262) Xuan-Son Nguyen 2026-08-17 18:21:02 +02:00
  • 992368d6cf group hashes into one single static lib xsn/vendor_hash Xuan Son Nguyen 2026-08-17 15:26:16 +02:00
  • 34af94cd9a ci : push release tag explicitly in release.yml (#27261) v0.1.1 b10470 Georgi Gerganov 2026-08-17 16:14:13 +03:00
  • 7a198bad4e vendor: move hash to vendor Xuan Son Nguyen 2026-08-17 15:12:41 +02:00
  • 666f8898a2 ui: move get_datetime tool to frontend (#27255) Xuan-Son Nguyen 2026-08-17 14:33:55 +02:00
  • f990aa7065 server: drop the now unused ctime include xsn/ui_get_datetime Pascal 2026-08-17 14:27:18 +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
  • 480fedca78 Merge remote-tracking branch 'origin/master' into xsn/ui_get_datetime Xuan Son Nguyen 2026-08-17 13:19:40 +02:00
  • 7077abbe14 ui: add browser get_info tool (#27251) Xuan-Son Nguyen 2026-08-17 13:14:33 +02:00
  • a27cf9ce2f Update tools/ui/src/lib/stores/tools.svelte.ts xsn/ui_get_info Xuan-Son Nguyen 2026-08-17 13:06:33 +02:00
  • 5a61d48d08 clarify docs Xuan Son Nguyen 2026-08-17 12:57:02 +02:00
  • 35293d0bb0 ui: move get_datetime tool to frontend Xuan Son Nguyen 2026-08-17 12:52:12 +02:00
  • 26dde08faf nits Xuan Son Nguyen 2026-08-17 12:35:10 +02:00
  • 2b96e7c35b format Xuan Son Nguyen 2026-08-17 12:32:48 +02:00
  • 94dc109ac4 ui: add browser get_info tool Xuan Son Nguyen 2026-08-17 12:32:15 +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
  • 49a5623688 simply cap to 1024 xsn/preprocessor_granite_harden Xuan Son Nguyen 2026-08-17 11:10:53 +02:00
  • fe48425719 convert: add test_convert.py xsn/convert_test Xuan Son Nguyen 2026-08-17 11:07:16 +02:00
  • 7c35571e5d ci : allow make-release to target a specific commit (#27234) v0.1.0 Georgi Gerganov 2026-08-17 11:52:46 +03:00
  • 079c75500f mtmd: harden preprocessor_granite Xuan Son Nguyen 2026-08-17 10:48:30 +02:00
  • 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
  • b4e5d8b616 rm pocket-tts xsn/convert_add_example Xuan Son Nguyen 2026-08-17 10:14:14 +02:00
  • 9edb2d2dba BailingMoeV3ForCausalLM Xuan Son Nguyen 2026-08-17 10:11:26 +02:00
  • 507ace2827 Merge branch 'master' into xsn/convert_add_example Xuan Son Nguyen 2026-08-17 10:09:07 +02:00
  • 3733366720 model : BailingMoE3 Support (#26608) Toby 2026-08-17 03:49:49 -04:00
  • 6e97dc0518 add more variants Xuan Son Nguyen 2026-08-17 09:12:19 +02:00
  • 04a134c70b ci : make release workflows use a deply key tmp-testing-0 gg/test-tag Georgi Gerganov 2026-08-17 09:58:11 +03:00
  • 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) b10456 Titaniumtown 2026-08-16 21:32:16 -07:00
  • 37a215c9e9 [SYCL] support OP OPT_STEP_ADAMW, OPT_STEP_SGD (#25268) b10455 Neo Zhang 2026-08-17 12:31:29 +08:00
  • 584b4f93c6 add docs Xuan Son Nguyen 2026-08-17 02:36:33 +02:00
  • 71c7866a16 convert: add @ModelBase.example Xuan Son Nguyen 2026-08-17 02:31:10 +02:00
  • 051139f511 conversion: refactor moe exp tensor handling xsn/convert_refactor_moe Xuan Son Nguyen 2026-08-17 01:54:08 +02:00
  • d2fd589f51 training: fix no KV cache Xuan Son Nguyen 2026-08-16 21:06:08 +02:00
  • 4df29be4f4 ci : fix dry-run reporting in make-release job [no ci] (#27167) b10454 Daniel Bevenius 2026-08-16 14:53:13 +02:00
  • 3cb7ffb1a1 model : remove some ggml_concat (#27176) b10453 fairydreaming 2026-08-16 14:12:55 +02:00
  • b94041a98e chat: refactor handling supports_string_content / supports_typed_content (#27130) b10452 Xuan-Son Nguyen 2026-08-16 12:45:33 +02:00
  • d31babce1e ui: npm run format for new upstream formatting rules xsn/remote_server Pascal 2026-08-16 09:08:43 +02:00
  • b3fe01f4d3 ui: use arrow function in fetch interceptor Pascal 2026-08-16 09:07:08 +02:00
  • aed7c384f5 ui: (demo) access server remotely via webrtc Xuan Son Nguyen 2026-06-13 16:30:26 +02:00
  • 10bf611e53 llama : check LoRA tensor data is within file bounds (#27056) b10451 Oğuzhan Akkaya 2026-08-16 02:38:01 -04:00
  • ece963f41b ui: mask API Key field in settings and error splash to stop browser a… (#26562) b10450 Cristiano Pinto 2026-08-15 21:52:55 +01:00
  • 27c299a6ec wip xsn/kimi-k3-optim Xuan Son Nguyen 2026-08-15 22:40:41 +02:00
  • 0d9ceae1e3 ui: read structuredContent from MCP tool result when content is empty (#26691) Gautam0507 2026-08-15 23:30:18 +05:30
  • ad1de39e07 model: add Kimi-K3 text model (#26185) b10448 Piotr Wilkin (ilintar) 2026-08-15 17:11:05 +02:00
  • 5f4001e047 rm cuda supports_op guard, fix webgpu clang-format Xuan Son Nguyen 2026-08-15 17:01:02 +02:00
  • 22b8e310b9 server: re-design yield_to_queue thread model (#27133) b10447 Xuan-Son Nguyen 2026-08-15 16:48:40 +02:00
  • 9871d51fd7 swap worker <--> main thread design xsn/fix_yield_to_queue Xuan Son Nguyen 2026-08-15 16:00:56 +02:00
  • 51a4f6303b run common_speculative_process in worker Xuan Son Nguyen 2026-08-15 15:39:14 +02:00
  • 8f75594531 ggml: (cuda) support ggml_rope_set_offset (#27121) Xuan-Son Nguyen 2026-08-15 15:35:17 +02:00
  • 14ae5ffc7b messages_inp_normalizer xsn/jinja_supports_string_content Xuan Son Nguyen 2026-08-15 14:47:40 +02:00
  • adb55e5148 vendor: update BoringSSL to 0.20260813.0 (#27099) b10446 Alessandro de Oliveira Faria (A.K.A.CABELO) 2026-08-15 08:41:18 -03:00
  • 77140d247c vendor : update cpp-httplib to 0.53.1 (#27103) Alessandro de Oliveira Faria (A.K.A.CABELO) 2026-08-15 08:40:44 -03:00
  • 5f754ea0e2 common: support --models-dir loading MTP assistant models (#24431) b10444 Eric Zhang 2026-08-15 19:17:35 +08:00
  • 820400abe1 test: add "skip" Xuan Son Nguyen 2026-08-15 13:12:17 +02:00
  • 37e7235645 better supports_string_content cap detect Xuan Son Nguyen 2026-08-15 13:06:26 +02:00
  • 71877ea54d gate other backends Xuan Son Nguyen 2026-08-15 12:47:15 +02:00
  • be16bac40b ggml: (cuda) support ggml_rope_set_offset xsn/ggml_rope_off_cuda Xuan Son Nguyen 2026-08-15 12:35:06 +02:00
  • c74aef2770 add test backend ops Xuan Son Nguyen 2026-08-15 12:20:50 +02:00
  • 53845a366e metal kernel Xuan Son Nguyen 2026-08-15 12:07:24 +02:00
  • b5464b9310 cpu kernel Xuan Son Nguyen 2026-08-15 12:01:29 +02:00
  • 48820ce356 add params Xuan Son Nguyen 2026-08-15 11:48:39 +02:00
  • 27df9199d1 fix: check gguf array type before reading (#27075) b10443 Xuan-Son Nguyen 2026-08-15 11:45:30 +02:00
  • 9b0a2ce859 vulkan: add SHMEM_STRIDE_PAD/APPLY_SLM_A_RESHAPE for coopmat1 on Intel Xe (#25380) b10442 Jiang, Fish 2026-08-15 17:35:05 +08:00
  • 0177dcc730 common: migrate the deprecated --mmap/--no-mmap to --load-mode (#26934) b10441 Fathi Boudra 2026-08-15 10:35:53 +02:00
  • 6b4344ecc7 fixed indent Masato Nakasaka 2026-08-14 11:47:55 +09:00
  • 7b38cb71b9 Fixed gating logic for problematic Intel driver version Masato Nakasaka 2026-08-14 10:39:51 +09:00
  • 9d57ce456c mtmd: fix Granite4 Vision image sequence assembly (#26653) b10438 Hemanth Battu 2026-08-14 15:25:26 -07:00
  • 16d222fc5e model : add support for MiniMaxText01ForCausalLM and MiniMaxM1ForCausalLM (#27018) b10437 fairydreaming 2026-08-15 00:02:38 +02:00
  • 6fed9f6ff7 mtmd, common: various fixes (#27071) b10436 Xuan-Son Nguyen 2026-08-14 23:34:56 +02:00
  • 9e40df63ba jinja : fix quadratic cost in gather_string_parts (#27034) b10435 0 2026-08-14 17:34:40 -04:00
  • 7e4c0a9688 chat : pass reasoning_effort to template b10434 Andy Williams 2026-08-15 03:53:11 +09:30
  • 045ec92f2d update skill xsn/assert_gguf_array_type Xuan Son Nguyen 2026-08-14 18:18:09 +02:00
  • faaf2efd3a fix: check gguf array type before reading Xuan Son Nguyen 2026-08-14 18:14:58 +02:00
  • 9b05354ec6 sync : ggml b10433 Georgi Gerganov 2026-08-14 19:05:40 +03:00
  • 06ae2326ba ggml : bump version to 0.20.0 (ggml/1584) Georgi Gerganov 2026-08-14 18:13:36 +03:00
  • fd6e36310f revert gguf fix xsn/security_audit_0 Xuan Son Nguyen 2026-08-14 17:47:26 +02:00
  • 57270316a8 cont Xuan Son Nguyen 2026-08-14 17:38:02 +02:00
  • b4e10fc595 impl mtmd cpp Xuan Son Nguyen 2026-08-14 17:34:27 +02:00
  • b8c0db704a apply fixes Xuan Son Nguyen 2026-08-14 17:31:38 +02:00
  • 1692f9e50b ggml : recurrent state rollback for ggml_ssm_scan (#26623) b10431 lnigam 2026-08-14 19:50:40 +05:30
  • 52e9954892 cont : fix gg/rpc-log-transport Georgi Gerganov 2026-08-14 17:15:50 +03:00
  • 1aa98bbe67 cont : fix Georgi Gerganov 2026-08-14 17:15:21 +03:00