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

  • d5120bcbff mtmd: conversion Xuan Son Nguyen 2026-08-14 16:14:41 +02:00
  • 5beb19ad71 cont : more logs Georgi Gerganov 2026-08-14 17:13:45 +03:00
  • 8eca1cd5e4 cont : fix Georgi Gerganov 2026-08-14 16:52:46 +03:00
  • 0fdb83ec6f cont : fix Georgi Gerganov 2026-08-14 16:50:49 +03:00
  • cd8860a09b cont : add <string> Georgi Gerganov 2026-08-14 16:49:47 +03:00
  • 511fa698f5 rpc : make RDMA probe diagnostics more verbose Georgi Gerganov 2026-08-14 16:45:29 +03:00
  • 8d4c022ee8 rpc : log the actual network transport in use Georgi Gerganov 2026-08-14 16:33:09 +03:00
  • 7c26c91500 set coarser granularity for head splits dsv4-sm-tensor Aman Gupta 2026-08-03 18:28:59 +02:00
  • 7b07e05c1e DSV4: sm tensor Aman Gupta 2026-07-31 05:38:35 +02:00
  • bcc7c630f8 metal: mul_mat: fix src1 row stride edge cases with has_tensor xsn/metal-fix-mm Xuan Son Nguyen 2026-08-14 14:28:08 +02:00
  • 4c1a0af40d llama : allow virtual igpu devices (#26953) b10430 Georgi Gerganov 2026-08-14 15:14:19 +03:00
  • 77918caf30 server: allow accessing /metrics and /slots during llama_decode() (#27041) b10429 Xuan-Son Nguyen 2026-08-14 13:23:10 +02:00
  • 25b654c74b init impl Xuan Son Nguyen 2026-08-14 13:21:21 +02:00
  • 5784322b14 text: conversion Xuan Son Nguyen 2026-08-14 12:13:32 +02:00
  • 3d6761b8f5 rm test xsn/non_blocking_metrics Xuan Son Nguyen 2026-08-14 12:03:50 +02:00
  • 885c5bbe8e tests : replace personal home directory paths with generic placeholders (#27043) b10428 Jim Wu 2026-08-14 01:32:59 -07:00
  • 6509138622 sycl: fuse mul_mat(gate) + mul_mat(up) + GLU for q4_K dense FFN (#26779) b10427 Titaniumtown 2026-08-13 23:26:23 -07:00
  • c6f6a92c55 ggml: force single thread on wasi (#25686) b10426 Mendy Berger 2026-08-14 02:16:20 -04:00
  • 3d93885352 sycl: fuse the gated-delta-net state writeback cpy (#26643) b10425 Titaniumtown 2026-08-13 23:00:36 -07:00
  • 2bacf9ea5c dflash : clarify output logging of target_layer_ids (#27013) b10424 Daniel Bevenius 2026-08-14 06:57:05 +02:00
  • 98e489eb6e nits Xuan Son Nguyen 2026-08-14 00:47:07 +02:00
  • d809c0f3ab clean up Xuan Son Nguyen 2026-08-14 00:42:29 +02:00
  • a35d2af15f also handle process_mtmd_chunk Xuan Son Nguyen 2026-08-13 23:54:19 +02:00
  • 0b42458e10 call llama_decode inside yield_to_queue Xuan Son Nguyen 2026-08-13 23:42:30 +02:00
  • a94d563ed8 common: apply CPU parameters across tools (#27026) b10423 Niklas Wenzel 2026-08-13 20:40:59 +02:00
  • bdffafa5df ui: Refactor data-attrs constants, enum for bool strings (#27002) Aleksander Grygier 2026-08-13 20:01:12 +02:00
  • fa4ec4590c refactor: Naming (#27001) Aleksander Grygier 2026-08-13 19:45:32 +02:00
  • 9c5531e2bf ui: fix VITE_PUBLIC_SERVER variable reading (#24845) Ilya 2026-08-13 20:31:51 +03:00
  • aee56b3abf OpenVINO: Qwen3.5, memory optimization, and test-recurrent-state-rollback (#26952) b10419 Zijun Yu 2026-08-14 01:30:48 +08:00
  • a97123e497 [SYCL] Support host pinned mem to improve SYCL Host-to-Device Memory Access (#26789) b10418 Neo Zhang 2026-08-14 01:05:33 +08:00
  • fca1761217 server_queue::worker Xuan Son Nguyen 2026-08-13 18:59:41 +02:00
  • 2606220d9f chat : fix LFM2 tool call arg name prefix ambiguity (#26960) b10417 Aldehir Rojas 2026-08-13 11:18:44 -05:00
  • 981184e49a server : serve index.html with no-cache (#27006) b10416 Emanuil Rusev 2026-08-13 17:59:45 +03:00
  • 1d2869c6e5 spec : auto-detect mtp draft model type (#27005) b10415 Sigbjørn Skjæret 2026-08-13 13:39:16 +02:00
  • 4a84b0ad10 metal : add TQ2_0 support (#26980) b10414 Georgi Gerganov 2026-08-13 14:33:53 +03:00
  • f65e568fd8 common : auto-detect spec type from draft GGUF metadata (#26814) b10413 aic0d3r 2026-08-13 12:34:27 +02:00
  • 0d0bfcd4fd spec: enable backend sampling for both dflash & dspark (#26958) b10412 Ruixiang Wang 2026-08-13 11:07:28 +02:00
  • eeae28b67e ggml-cpu/ops: vectorize flash-attention V-cache F16 to F32 conversion (#26947) b10411 jinzihao 2026-08-13 17:04:46 +08:00
  • 154d57af3e sycl: remove separate fp32 type promotion in gemm non-oneDNN path (#26372) b10410 Ian Faust 2026-08-13 11:02:18 +02:00
  • 1ee1cd9bc6 sycl: fuse UNARY(silu|sigmoid|softplus) + MUL (#26411) Titaniumtown 2026-08-13 01:41:38 -07:00
  • 8efbf65dbd sycl : Add DMMV ESIMD Q3_K kernel (#26251) b10408 Todd Malsbary 2026-08-13 01:32:36 -07:00
  • d415e65a57 sycl : enhance concat to support Q4_0, Q4_1, Q5_0, Q5_1, Q8_0 (#26800) Neo Zhang 2026-08-13 16:24:28 +08:00
  • decaf508bb server: refactor + correctness fixes for metrics (#26920) Xuan-Son Nguyen 2026-08-13 10:02:01 +02:00
  • e79e4bf660 ggml-hip : remove -funsafe-math-optimizations (#26696) b10405 Jim Wu 2026-08-12 23:38:02 -07:00
  • d86c7d62df ui: Clean up contexts, remove prop drilling from Chat Form Actions (#26951) Aleksander Grygier 2026-08-13 08:21:15 +02:00
  • f2efd64141 ui: Move styles/ to $lib scope (#26950) Aleksander Grygier 2026-08-13 08:13:52 +02:00
  • 094e53db1c ui: Stores architecture improvements (#26910) Aleksander Grygier 2026-08-13 08:11:30 +02:00
  • a6040c925c refactor: Clean up UI types (#26909) Aleksander Grygier 2026-08-13 08:07:34 +02:00
  • 1f368f354d ggml : fix arm builds, unused var (#26991) b10400 Georgi Gerganov 2026-08-13 07:57:24 +03:00
  • e21152dc96 ui: Constants refactor (#26908) Aleksander Grygier 2026-08-13 06:53:56 +02:00
  • 8e7f22b67e common: add system-level config file (#26118) b10398 Johnathan Craig Maudlin 2026-08-12 18:02:27 -04:00
  • 84e908c625 ci: fix thread sanitizer + remove ccache (#26927) Eve 2026-08-12 16:01:12 +00:00
  • b7d9c4ccaf nits xsn/refactor_server_metrics Xuan Son Nguyen 2026-08-12 17:19:57 +02:00
  • 27615964d0 rm dead code Xuan Son Nguyen 2026-08-12 17:07:46 +02:00
  • ef51649a65 cont Xuan Son Nguyen 2026-08-12 17:00:06 +02:00
  • a46d5259d7 fix flush before reset() Xuan Son Nguyen 2026-08-12 16:43:09 +02:00
  • c53ad20164 nits Xuan Son Nguyen 2026-08-12 15:45:23 +02:00
  • 9558fa44c9 ci : disable ubuntu-rocm (#26969) Sigbjørn Skjæret 2026-08-12 15:41:44 +02:00
  • 7a9ff95979 disable rocm cache (#26962) Sigbjørn Skjæret 2026-08-12 15:41:43 +02:00
  • 9138c133ba add test Xuan Son Nguyen 2026-08-12 15:39:36 +02:00
  • 9c57fd783c refactor server_task_result_metrics Xuan Son Nguyen 2026-08-12 14:16:11 +02:00
  • 680a9ae63d cmake : introduce semantic versioning (#26839) Daniel Bevenius 2026-08-12 14:15:03 +02:00
  • d8a8beac22 gguf : harden loader against malformed tensor dims and metadata types (#25596) HarrisonSec 2026-08-12 05:07:48 -07:00
  • e0f113decb metrics: seperate cache/processed prompt tokens Xuan Son Nguyen 2026-08-12 13:54:36 +02:00
  • 132753bf4e kleidiai: Add runtime feature detection mechanism for aarch64/kleidiai (#26076) Jonathan Clohessy 2026-08-12 12:49:11 +01:00
  • a55abe44aa metrics_flush_idle Xuan Son Nguyen 2026-08-12 13:47:09 +02:00
  • 6849901f4a metrics_on_prediction Xuan Son Nguyen 2026-08-12 13:42:03 +02:00
  • 509866bc9b n_predict --> n_gen Xuan Son Nguyen 2026-08-12 13:38:03 +02:00
  • 372ea5734d more accurate batch metrics tracking Xuan Son Nguyen 2026-08-12 13:25:43 +02:00
  • ece98b87f7 model : disallow integer dflash sliding_window_pattern (#26900) Sigbjørn Skjæret 2026-08-12 13:24:10 +02:00
  • af05a42a7c sync : ggml Georgi Gerganov 2026-08-12 13:59:44 +03:00
  • 13fd0bb55e cmake : add config version support (ggml/1582) Daniel Bevenius 2026-08-12 12:46:06 +02:00
  • 5d9e5ac30e server : support slot save/restore with media inputs (#26640) Chipmunk 2026-08-12 19:20:28 +09:00
  • 4dd127584b ui: add read_media tool (#25877) parabelboi 2026-08-12 12:03:32 +02:00
  • 20ce126733 exclude first generated token Xuan Son Nguyen 2026-08-12 12:01:01 +02:00
  • 89e0aa6fd3 opencl: default FA c8 cluster width to 16 on X1E (#26433) Hongqiang Wang 2026-08-11 23:10:27 -07:00
  • a4a4c51f3d tests : update speculative params (#26925) Georgi Gerganov 2026-08-12 08:08:19 +03:00
  • a7cd2f0e98 vulkan: add TQ2_0 (ternary) support (#25850) michaeltrabalka-tech 2026-08-12 01:07:23 -04:00
  • 55f453b924 wavtokenizer-dec : bound posnet/convnext block_count against n_layer_all (#26892) Oğuzhan Akkaya 2026-08-12 01:06:16 -04:00
  • 6eff593262 convert : handle per_layer_config in Gemma4 (transformers 5.15) (#26882) Wang Zhiyu 2026-08-12 13:05:13 +08:00
  • cb27fe9c35 opencl: use flat mv q5_k when weight exceeds image1d_buffer_t limit (#26880) lhez 2026-08-11 22:02:28 -07:00
  • a2fd44e35f nits: move place in code Xuan Son Nguyen 2026-08-12 02:28:33 +02:00
  • 2581e568df cont Xuan Son Nguyen 2026-08-12 02:23:31 +02:00
  • 7d59fa387a tie stats to batch Xuan Son Nguyen 2026-08-12 02:01:33 +02:00
  • 75d2de4bac rm result_timings Xuan Son Nguyen 2026-08-12 00:33:11 +02:00
  • b16f898b2a cont Xuan Son Nguyen 2026-08-12 00:22:09 +02:00
  • 22170592bb move most fields to server_slot_stats Xuan Son Nguyen 2026-08-11 23:14:51 +02:00
  • 0b1bad14ff chat : fix muse-glimmer detection of tool calls after EOM (#26879) b10380 ruanslv 2026-08-11 16:15:20 -04:00
  • 7b13a8404d ci : add missing release check (#26923) Sigbjørn Skjæret 2026-08-11 20:20:40 +02:00
  • ebb546b7e9 CUDA: only disable CUDA graphs when mul_mat_id actually needs a stream sync (#26802) Rafail Giavrimis 2026-08-11 18:50:03 +01:00
  • 5988633170 cuda : add warp-per-row wkv7 kernel for single-token decode (#26111) 0 2026-08-12 01:46:23 +08:00
  • 14bb119b2e server: refactor metrics Xuan Son Nguyen 2026-08-11 19:20:47 +02:00
  • f785fc9ea4 spec : update speculative-simple (#26904) Georgi Gerganov 2026-08-11 19:52:12 +03:00
  • ba360efe1f chat : tighten bare function parsing for Qwen models (#26793) b10375 Aldehir Rojas 2026-08-11 10:58:54 -05:00
  • 70dfba5aee ci : add windows-rocm to check-release (#26897) Sigbjørn Skjæret 2026-08-11 17:48:27 +02:00
  • 38406d597f imatrix.cpp: Move finite check and only check touched experts (#26861) b10373 Bartowski 2026-08-11 11:18:19 -04:00
  • 2468576f24 requirements: use stable torch packages on s390x (#26864) Niklas Wenzel 2026-08-11 15:58:53 +02:00
  • 5d16e81dd9 convert : keep quantization scales for nemotron --mtp export (#26903) ynankani 2026-08-11 13:19:05 +00:00
  • cc078b45b6 Dflash support for nemotron-3.5 (#26905) lnigam 2026-08-11 18:46:26 +05:30
  • 6e62ba5384 mtmd: support pocket-tts (#26871) b10369 Xuan-Son Nguyen 2026-08-11 14:18:30 +02:00