Commit Graph

Select branches

Hide Pull Requests

mtp-turboquant

Mono Color

• 745fa0e78b model : add glm-asr support (#17901) piDack 2025-12-15 10:18:46 +08:00
• 52392291b2 preset: handle negated arg, reverse the meaning if needed (#18041) Xuan-Son Nguyen 2025-12-14 22:08:10 +01:00
• 5c8a717128 convert : refactor rope scaling handling (#18013) Sigbjørn Skjæret 2025-12-14 16:04:37 +01:00
• 37f5a1093b mtmd: enhance image resizing in llava_uhd (#18014) Haowei Wu 2025-12-14 22:57:52 +08:00
• 9e6649ecf2 vulkan: fix mul_mat_vec_iq1_s formatting (#18026) Ruben Ortlam 2025-12-14 14:52:46 +01:00
• 0759b09c90 graph: add f_attn_temp_offset (#18025) Xuan-Son Nguyen 2025-12-14 13:05:59 +01:00
• 254098a279 common : refactor common_sampler + grammar logic changes (#17937) Georgi Gerganov 2025-12-14 10:11:13 +02:00
• 3238b1400c vulkan: Fix data race/hang in scalar/cm1 flash attention (#17887) Jeff Bolz 2025-12-14 02:00:00 -06:00
• 4722671641 vulkan: improve mul_mat_vec_iq1_s speed (#17874) lovedheart 2025-12-14 08:47:49 +01:00
• d15d177f43 vulkan: faster q6_k matmul (#17813) Eve 2025-12-14 07:29:37 +00:00
• 77ad8542bd model-conversion : cast logits to float32 (#18009) Georgi Gerganov 2025-12-14 08:58:13 +02:00
• 609a2d0268 models : fix YaRN regression + consolidate logic (#18006) Georgi Gerganov 2025-12-14 08:34:56 +02:00
• a63cbafbbc ggml : arm repack fix build Georgi Gerganov 2025-12-13 22:54:14 +02:00
• 0e59224990 sync : ggml Georgi Gerganov 2025-12-13 10:07:07 +02:00
• 71fdcf0616 ggml : arm repack fix build (whisper/0) Georgi Gerganov 2025-12-13 08:04:09 +02:00
• 615655aafe cmake : set CMAKE_RUNTIME_OUTPUT_DIRECTORY for non standalone build (ggml/1394) Congcong Cai 2025-12-12 22:37:38 +08:00
• c00ff929dc scripts: add script to compare logprobs of llama.cpp against other frameworks (#17947) Xuan-Son Nguyen 2025-12-13 22:33:29 +01:00
• 4ed2bae50d server-models.cpp: add missing <filesystem> (#18000) Sergey Fedorov 2025-12-14 05:02:43 +08:00
• 5266379bca llama_context: synchronize before reallocating output buffer (#17974) Jeff Bolz 2025-12-13 09:19:51 -06:00
• 4d5ae24c0a arg: fix common_params_parse not accepting negated arg (#17991) Xuan-Son Nguyen 2025-12-13 12:53:37 +01:00
• 66ba51252e cmake: correct scope - link ws2_32 for MinGW/w64devkit builds in cpp-httplib (#17972) Gustavo Rocha Dias 2025-12-13 08:46:36 -03:00
• 36255a2268 vulkan: support get_rows for i32 (#17941) Jeff Bolz 2025-12-13 03:12:53 -06:00
• 3229a23fa6 vulkan: support GGML_OP_DIAG (#17893) Jeff Bolz 2025-12-13 03:07:49 -06:00
• 303f8615e9 vulkan: Multi-pass softmax for large number of cols (#17892) Jeff Bolz 2025-12-13 03:04:29 -06:00
• 3c6391e748 speculative-simple : free batch on exit (#17985) Georgi Gerganov 2025-12-13 09:48:34 +02:00
• 8e4d678528 common : skip model validation when --completion-bash is requested (#17975) Sigbjørn Skjæret 2025-12-13 08:40:50 +01:00
• 07a10c1090 vulkan: Allow non-pow2 n_experts in topk_moe (#17872) Jeff Bolz 2025-12-13 01:40:04 -06:00
• 2bc94e7928 add llama-completion to completion-bash executables (#17976) Sigbjørn Skjæret 2025-12-13 08:35:50 +01:00
• fd1085ffb7 model-conversion : use CONVERTED_MODEL value for converted model [no ci] (#17984) Daniel Bevenius 2025-12-13 08:34:26 +01:00
• 380b4c984e common: support negated args (#17919) Xuan-Son Nguyen 2025-12-12 23:58:53 +01:00
• e39a2ce66d clip: move model cgraphs into their own files (#17965) Xuan-Son Nguyen 2025-12-12 21:14:48 +01:00
• a8c7f33d79 ci : change the cann version and the container pull method (#17953) jiahao su 2025-12-13 03:43:00 +08:00
• b7f5f46e03 docker : include legacy llama-completion binary (#17964) Sigbjørn Skjæret 2025-12-12 19:39:23 +01:00
• 482211438d CUDA: fix overflow in MMA kernel without stream-k (#17939) Johannes Gäßler 2025-12-12 17:43:58 +01:00
• 7bed317f53 models : fix the attn_factor for mistral3 graphs + improve consistency (#17945) Georgi Gerganov 2025-12-12 17:12:40 +02:00
• dcb7d17758 cann : fix ops broken by circular padding guard (#17825) Sigbjørn Skjæret 2025-12-12 15:49:27 +01:00
• 51604435e8 ggml-cpu : fix RISC-V Q4_0 repack select and RVV feature reporting (#17951) ixgbe 2025-12-12 22:26:03 +08:00
• 17158965ac mtmd: explicitly forbidden inclusion of private header and libcommon (#17946) Xuan-Son Nguyen 2025-12-12 15:16:06 +01:00
• 12280ae905 webui: Fix parsing non-LaTeX occurrencies of \( or \) (#17810) Aleksander Grygier 2025-12-12 15:13:36 +01:00
• 54a0fee4b7 arg: add -mm and -mmu as short form of --mmproj and --mmproj-url (#17958) Xuan-Son Nguyen 2025-12-12 14:06:06 +01:00
• dada4c846d model-conversion : remove max diff check in compare-logits [no ci] (#17954) Daniel Bevenius 2025-12-12 13:25:16 +01:00
• b8ee22cfde common : add minimalist multi-thread progress bar (#17602) Adrien Gallouët 2025-12-12 12:44:35 +01:00
• 2eaa2c65cb cmake: link ws2_32 for MinGW/w64devkit builds in cpp-httplib (#17949) Gustavo Rocha Dias 2025-12-12 08:02:28 -03:00
• c33a58bced HIP: enable mmf for RDNA3 (#17879) yulo 2025-12-12 18:34:33 +08:00
• a81a569577 Add a search field on model selector / improve mobile display (#17765) Pascal 2025-12-11 18:21:21 +01:00
• 53ecd4fdb9 SOLVE_TRI extension to more dimensions (#17793) Piotr Wilkin (ilintar) 2025-12-11 17:20:43 +01:00
• c6f6e4f96a ggml-alloc : fix reuse-parent logic for misaligned sizes (#17884) Georgi Gerganov 2025-12-11 14:30:10 +02:00
• d9f8f60618 batch : fix sequence id ownership (#17915) Georgi Gerganov 2025-12-11 14:29:47 +02:00
• e4ae383317 docs: use port 8080 in Docker examples (#17903) Yuichiro Utsumi 2025-12-11 18:12:07 +09:00
• 34ce48d97a ggml-hexagon: fix rope failure at test-backend-ops (#17565) nullname 2025-12-11 06:45:43 +08:00
• 45e350e3d3 ci: fix riscv64-native build (#17916) Sigbjørn Skjæret 2025-12-10 23:24:31 +01:00
• c6b2c9310c mtmd: some small clean up (#17909) Xuan-Son Nguyen 2025-12-10 22:20:06 +01:00
• 34a6d86982 cli: enable jinja by default (#17911) Xuan-Son Nguyen 2025-12-10 22:19:42 +01:00
• f32ca51bfe server: add presets (config) when using multiple models (#17859) Pascal 2025-12-10 22:18:21 +01:00
• e1f4921980 Fix race conditions in threadpool when dealing with dynamic/frequent n_threads changes (#17748) Max Krasnyansky 2025-12-10 12:32:23 -08:00
• 4dff236a52 ggml : remove GGML_KQ_MASK_PAD constant (#17910) Georgi Gerganov 2025-12-10 20:53:16 +02:00
• 4df6e859e9 cuda : add missing support check for xielu (#17895) Sigbjørn Skjæret 2025-12-10 16:16:20 +01:00
• 6c2131773c cli: new CLI experience (#17824) Xuan-Son Nguyen 2025-12-10 15:28:59 +01:00
• b677721819 model : Qwen3-Next-80B-A3B has 48 layers (#17898) Eric Zhang 2025-12-10 22:22:40 +08:00
• 2d2e1030e3 docs : update opencl ops (#17904) lhez 2025-12-10 06:20:00 -08:00
• 17f7f4baad CUDA: fix unpadded strides in MMA FA kernel (#17891) Johannes Gäßler 2025-12-10 12:39:56 +01:00
• 9e79b0116e convert: allow using quantized Mistral weight (#17889) Xuan-Son Nguyen 2025-12-10 10:26:22 +01:00
• 2e9eab80c2 fix softmax for iGPU (#17838) Neo Zhang Jianyu 2025-12-10 16:59:57 +08:00
• 2fbe3b7bb7 common : add parser for ministral/mistral large 3/devstral 2 (#17713) Aldehir Rojas 2025-12-09 17:31:04 -06:00
• 63391852b0 docs : update cpu and cuda ops (#17890) Sigbjørn Skjæret 2025-12-09 23:31:29 +01:00
• 086a63e3a5 metal: SSM kernel improvements (#17876) Gabe Goodhart 2025-12-09 12:30:02 -07:00
• b63509262a Add DIAG for CUDA (#17873) Piotr Wilkin (ilintar) 2025-12-09 20:28:57 +01:00
• 48f47565a7 docs: clarify that CPU support should be first (#17886) Johannes Gäßler 2025-12-09 20:10:36 +01:00
• 02e409a5be ggml : Provide macos-specific backtrace printing to avoid terminal death (#17869) Gabe Goodhart 2025-12-09 09:29:07 -07:00
• 6b82eb7883 metal : print node names for debugging (#17882) Georgi Gerganov 2025-12-09 15:25:49 +02:00
• 86a3f0fad8 ggml : allow fill node alloc inplace (#17870) Sigbjørn Skjæret 2025-12-09 12:23:47 +01:00
• 63908b631a cmake: fix Mach-O current version number (#17877) Rhys-T 2025-12-09 06:17:41 -05:00
• 42b12b5608 model : nit, DeepSeek V1 MoE is 16B and GigaChat is 20B (#12652) Sigbjørn Skjæret 2025-12-09 12:15:06 +01:00
• 4e842d5120 console: allow using arrow left/right, home/end keys and history mode (#17836) Xuan-Son Nguyen 2025-12-09 11:53:59 +01:00
• ca709e427b CANN: add support for partial RoPE and Vision mode (#17543) Chenguang Li 2025-12-09 17:53:23 +08:00
• 0cdce38a97 CUDA: fix FP16 overflow in tile FA kernel (#17875) Johannes Gäßler 2025-12-09 09:34:02 +01:00
• e39502e74b llama : add token matching support to llama-grammar (#17816) Aldehir Rojas 2025-12-09 00:32:57 -06:00
• 1d2a1ab73d model : support Rnj-1 (#17811) philip-essential 2025-12-08 19:49:03 -08:00
• c8554b66e0 graph : use fill instead of scale_bias in grouped expert selection (#17867) Sigbjørn Skjæret 2025-12-08 21:29:59 +01:00
• 2fa51c19b0 model-conversion : add token ids to prompt token output [no ci] (#17863) Daniel Bevenius 2025-12-08 17:13:08 +01:00
• 951520ddb0 server: delegate result_state creation to server_task (#17835) Xuan-Son Nguyen 2025-12-08 17:04:38 +01:00
• 68522c678d ci : support bfloat16 SYCL release package (#17855) Neo Zhang 2025-12-08 22:09:39 +08:00
• f896d2c34f server: improve speed of speculative decoding (#17808) Xuan-Son Nguyen 2025-12-08 14:35:28 +01:00
• e4e9c4329c Make graph_max_nodes vary by ubatch size (#17794) Piotr Wilkin (ilintar) 2025-12-08 14:32:41 +01:00
• 636fc17a37 Fix Kimi-K2 tool-call parsing issues (#17376) hksdpc255 2025-12-09 00:32:04 +11:00
• 51e0c2d917 cuda : add FILL op support (#17851) Jay Zenith 2025-12-08 05:10:12 -08:00
• 37a4f63244 server : add development documentation (#17760) Xuan-Son Nguyen 2025-12-08 13:54:58 +01:00
• 2bc96931d2 server : make cache_reuse configurable per request (#17858) Georgi Gerganov 2025-12-08 12:43:12 +02:00
• 5814b4dce1 cuda: optimize SOLVE_TRI using registers and FMAF (#17703) wsbagnsv1 2025-12-08 10:41:08 +01:00
• 79d61896d3 ggml-cpu: add ggml_thread_cpu_relax with Zihintpause support (#17784) ixgbe 2025-12-08 16:41:34 +08:00
• 4d3726278b model: add llama 4 scaling for mistral-large (deepseek arch) (#17744) Xuan-Son Nguyen 2025-12-07 22:29:54 +01:00
• 08f9d3cc1d Vulkan: improve mul_mat_vec_iq1_m (#16907) lovedheart 2025-12-07 18:40:42 +01:00
• 0a540f9abd ci : add windows-cuda 13.1 release (#17839) Sigbjørn Skjæret 2025-12-07 14:02:04 +01:00
• 22577583a3 common : change --color to accept on/off/auto, default to auto (#17827) Sigbjørn Skjæret 2025-12-07 03:43:50 +01:00
• d9e03db1e7 sycl: add missing BF16 conversion support for Intel oneAPI (#17780) Law Po Ying 2025-12-07 09:18:18 +08:00
• db97837385 vulkan: perf_logger improvements (#17672) Jeff Bolz 2025-12-06 11:46:46 -06:00
• 017761daf5 ggml-zendnn : add ZenDNN backend for AMD CPUs (#17690) Vishal Singh 2025-12-06 21:43:33 +05:30
• c42712b056 server: support multiple generations from one prompt (OAI "n" option) (#17775) Xuan-Son Nguyen 2025-12-06 15:54:38 +01:00
• 09c7c50e64 ggml : add circular tiling support to pad, for Vulkan, CUDA, and CPU (used for making seamless textures) (#16985) Phylliida Dev 2025-12-06 06:07:02 -08:00
• f334b79494 HIP: fix RDNA3 FP16/BF16 matrix multiplication (#17817) Johannes Gäßler 2025-12-06 13:45:36 +01:00