Commit Graph

Select branches

Hide Pull Requests

master

Mono Color

• 3bcfeb700f cmake : add PCH and unity build to improve build times (#28091) Daniel Bevenius 2026-09-11 13:01:29 +02:00
• 1dfe94e048 common : fix typo in speculative.cpp comment [no ci] (#28750) Daniel Bevenius 2026-09-11 12:59:43 +02:00
• a2878d30df metal : single-source fusion table + fusion debug rework (#28164) Georgi Gerganov 2026-09-11 12:41:54 +03:00
• aac810230f metal : fix idle threads in the remaining iq mul_mv kernels for ne00 < 1024 (#28692) Foad Abo Dahood 2026-09-11 12:30:20 +03:00
• 5cdd3d1dad model : fix MTP context kv cache allocation for deepseek2, glm4moe, … (#28630) Logan Chu 2026-09-11 02:02:31 -07:00
• b0dcb8192b server: fix speculation after an image (#28715) Jesus Gulfo 2026-09-11 03:33:26 -05:00
• 16378d93f9 CUDA/HIP: Flash Attention tuning (gfx1201) (#28102) Piotr Wilkin (ilintar)andJohannes Gäßler 2026-09-11 09:58:20 +02:00
• 451b89bae0 ci : key cache to sanitizer matrix (#28708) Sigbjørn Skjæret 2026-09-11 07:56:18 +02:00
• 481c65f091 vulkan: fix data race and OOB access in argsort(large) (#28705) Jeff Bolz 2026-09-11 00:44:13 -05:00
• df03399b88 opencl: add A8 Q4_0 mm binary kernel support (#28268) shaofeiqi 2026-09-10 11:25:40 -07:00
• 28ff095829 vulkan: use CPU writes in ggml_backend_vk_cpy_tensor_async if the context is idle (#28618) Jeff Bolz 2026-09-10 12:22:46 -05:00
• 50182a53fa vulkan: use add_alloc_dep to enable topk_moe fusion for prefill (#28422) Jeff Bolz 2026-09-10 12:21:29 -05:00
• 6788edb4f3 vulkan: small M matrix optimizations for qwen (#28457) Jeff Bolz 2026-09-10 12:20:18 -05:00
• 52d4268656 ci : add self-hosted-gpu-cuda and server-sanitize to hf-jobs (#28693) Sigbjørn Skjæret 2026-09-10 18:11:32 +02:00
• 18c17b4d66 ci : Update WoA CUDA 13.4 release to use 13.4.1 GA redistributables (#28687) shivamkumard-ctrl 2026-09-10 21:40:55 +05:30
• fa67698187 spec: fix failed to decode mtmd chunk with DFlash (#28587) Jesus Gulfo 2026-09-10 10:10:55 -05:00
• 41fc7584f0 scripts : use sed instead of grep for version parsing [no ci] (#28700) Daniel Bevenius 2026-09-10 15:44:40 +02:00
• d344123fe2 models: clean up some dead switch branches in old models (#28669) Iggy Jackson 2026-09-10 06:09:35 -07:00
• c32d1dabe8 tests : increase tolerance for Add fusion tests (#28691) Gaurav Garg 2026-09-10 17:42:40 +05:30
• e5a8d439ce tests : drop SYCL special-casing in test-backend-ops.cpp (#28688) Georgi Gerganov 2026-09-10 13:43:43 +03:00
• 3ff67eb43d vulkan: fall back to shared-memory reduction for dmmv on PowerVR (#28341) Julian Pscheid 2026-09-10 03:42:23 -07:00
• 8c322d5bc4 convert : expand Nemotron H conversion fix (#28689) Kartik GuliaandSigbjørn Skjæret 2026-09-10 16:11:57 +05:30
• 311d4211bf memory : avoid allocating V cache for indexer (it's not used) (#28330) fairydreamingandStanisław Szymczyk 2026-09-10 10:55:46 +02:00
• 72797e8919 vulkan : add command-buffer debug labels for GPU profilers (#28101) Cordell Blanchardandgabby-zy 2026-09-10 03:06:07 -04:00
• 4ea6d1bb6d ggml-cpu(s390x): add repack support for q4_0 (#28667) Aaron Teo 2026-09-10 14:51:17 +08:00
• f1b6fbf35c ggml-cpu(s390x): add Q1_0 vector intrinsic support (#28606) Aaron Teo 2026-09-10 14:50:28 +08:00
• d7e86430a7 model: fix all granite family parameter counts (#28643) Aaron Teo 2026-09-10 14:49:56 +08:00
• 434ddbbc0e ci: fix sanitizer tests (#28583) Eve 2026-09-09 19:46:28 +00:00
• 91f6a6cf36 vulkan: use spec constant for matrix matrix multiplication A-type (#25773) Ruben Ortlam 2026-09-09 18:53:39 +02:00
• 6d9c82ea2b hexagon: rope updates (#28628) Todor BoinovskiandMax Krasnyansky 2026-09-09 08:40:24 -07:00
• 22397c31a0 vulkan: Convert FILL to distribute workgroups in 2D to avoid exceeding maxComputeWorkGroupCount (#28592) Masato Nakasaka 2026-09-09 07:54:15 -07:00
• 4b98ab805a py : lower numpy to 2.2.6 (#28654) Sigbjørn Skjæret 2026-09-09 15:56:27 +02:00
• 9cf3bf256b py : bump numpy to 2.4.6 (#28649) Sigbjørn Skjæret 2026-09-09 14:59:37 +02:00
• 4850c7727f llama : use int32_t for llama_sampler_chain_n return type (#28631) linsen458-specandlinsen 2026-09-09 20:27:25 +08:00
• d4abd573f6 CUDA: size routed MoE MMQ N-tiles from typical expert width on RDNA3 (#28552) 3 people 2026-09-09 13:25:54 +02:00
• 5a4d0fecae CUDA: replace GGML_FA_ALL_QUANTS with GGML_FA_QUANTS, more control over what is compiled (#28079) Piotr Wilkin (ilintar)andJohannes Gäßler 2026-09-09 12:50:08 +02:00
• 14a9d09f75 args: officially deprecate --mmap|mlock|dio (#28334) Aaron Teo 2026-09-09 18:36:27 +08:00
• e2d2c0d6aa model: fix granite3 moe unknown parameter count (#28632) Aaron Teo 2026-09-09 16:46:22 +08:00
• 6de9cdb26b mtmd: propagate video ID to bitmap (#28601) Xuan-Son Nguyen 2026-09-09 10:37:36 +02:00
• b31b71f3a0 jinja: treat a null left operand of in as a plain lookup (#28620) Pascal 2026-09-09 09:08:27 +02:00
• df750f76bb vulkan: add dedicated iq4_xs mat-vec shader (#28426) WakeUpMorty 2026-09-09 08:26:36 +02:00
• 1945e09203 vulkan: add f16 B-type matmul pipelines and warp tile size tuning for Intel coopmat1 (#27471) Jiang, Fish 2026-09-09 14:03:32 +08:00
• 30b6a755e2 tests : use less threads for data initialization (#28325) Georgi Gerganov 2026-09-09 07:50:38 +03:00
• 304665fe7a Add IQ type handling for MoE (#28476) cwriterandcwriter 2026-09-09 03:25:41 +02:00
• f3f1a8f276 llama: disable lazy tensor loading by default on iGPUs (#28326) Ruben Ortlam 2026-09-08 18:05:09 +02:00
• 9113cc1880 ggml : fix msvc+clang ggml_vld1q_u32 (#28284) Sarah Wu 2026-09-08 07:40:26 -07:00
• d4389a4dd9 Revert "ggml-cuda : restore prop.integrated on HIP builds (#24233)" (#28604) uvos 2026-09-08 16:19:53 +02:00
• 5d806aa257 server : apply checkpoint min-step eviction only when the checkpoint list is full (#28302) Foad Abo Dahood 2026-09-08 16:01:03 +03:00
• 88ada91c18 metal : fix idle threads in mul_mv_iq3_xxs for ne00 < 1024 (#28086) Foad Abo Dahood 2026-09-08 15:54:42 +03:00
• 415e909d84 spec: single device drafter should create meta backend wrapper (#28390) Aman Gupta 2026-09-08 20:44:33 +08:00
• 03fa73cb27 ci : disable npm gha cache (#28600) Sigbjørn Skjæret 2026-09-08 14:06:15 +02:00
• 1744c6bde8 ci : add PYTEST_WORKERS=1 to fix server-self-hosted job (#28603) Daniel Bevenius 2026-09-08 13:36:03 +02:00
• ca86fb222e llama : add missing headers (#28566) Pepper Gray 2026-09-08 12:59:53 +02:00
• 64e9bceb2c vulkan : fuse UNARY(GELU|SIGMOID|SILU|SOFTPLUS) + MUL (#27220) Ankit Khandelwal 2026-09-08 13:05:02 +05:30
• f014bfef8b Fix Vulkan-Hpp handle usage on 32-bit targets. (#22892) miyan 2026-09-08 15:34:12 +08:00
• 895c045fd1 chat : split specialized parsers into common/parsers (#27764) Piotr Wilkin (ilintar) 2026-09-08 08:29:37 +02:00
• 7d701b5929 opencl: properly handle non-contiguous inputs to conv2d (#28503) lhez 2026-09-07 23:26:34 -07:00
• 5a6caa05fc ggml : update ggml_prec specification (#26675) Georgi Gerganov 2026-09-08 09:06:24 +03:00
• 9dcf84e5ae model : support Kimi-K3 recurrent-state rollback (#28466) Frank Dai 2026-09-07 20:31:48 -07:00
• 050dde50c9 hexagon: add RELU and LEAKY_RELU ops (#28585) Todor Boinovski 2026-09-07 17:04:25 -07:00
• 67672dc5b7 ci : bump ty to 0.0.78 (#28548) Sigbjørn Skjæret 2026-09-07 21:10:06 +02:00
• f114f91f9e tests : initialize the L2_NORM batch array (#28553) Pascal 2026-09-07 19:54:13 +02:00
• e71b80510c Revert "CUDA: size routed MoE MMQ N-tiles from typical expert width on RDNA3 (#24546)" (#28551) Piotr Wilkin (ilintar) 2026-09-07 16:28:19 +02:00
• ccc3646c63 nix : update deprecated expressions (#28145) Zhaolun Yin 2026-09-07 14:59:45 +01:00
• c0b1871bc7 webgpu: format the GET_ROWS case block (#28542) Pascal 2026-09-07 15:55:14 +02:00
• 160bd031b2 server: fix LRU hang on multiple requests same model (#28539) Xuan-Son NguyenandPascal 2026-09-07 15:50:46 +02:00
• dbeb37548e sycl: add a batched L2_NORM kernel (#28222) Titaniumtown 2026-09-07 06:24:14 -07:00
• 7a333e7240 vulkan: add DeepSeek-V4 hyper-connection fused ops (DSV4_HC_COMB/PRE/POST) (#26578) Kevin HopperandKevin Hopper 2026-09-07 08:24:03 -05:00
• 0c963452ea CUDA: size routed MoE MMQ N-tiles from typical expert width on RDNA3 (#24546) ravel7524andCarl Philipp Klemm 2026-09-07 09:22:42 -04:00
• 4735997382 ggml: add gfx90c HIP support (#26454) AuroraRAS 2026-09-07 22:21:42 +09:00
• d23c47f2a9 convert : refactor Hy4-preview conversion - move HC tensor mapping to the global map (#28451) fairydreamingandStanisław Szymczyk 2026-09-07 15:20:58 +02:00
• 73ab7599b5 CUDA: branchless Q4_K/Q5_K unpack to speed up mmvq, L2 prefetch on DGX Spark (#26705) Pranesh Gonegandlaandpraneshgo 2026-09-07 11:36:58 +00:00
• 0cae43063c vulkan: support type-aligned GET_ROWS (#28253) Jeff BolzandAiChiTuDouPian 2026-09-07 05:22:10 -05:00
• 1173700b9c examples : print ggml_version and ggml_commit in test-cmake [no ci] (#28538) Daniel Bevenius 2026-09-07 12:11:40 +02:00
• 5202104b59 caps : recheck typed content if template checks for string (#28511) Sigbjørn Skjæret 2026-09-07 09:14:32 +02:00
• 9a7570587c convert : write explicit recurrent_layers for Qwen3-Next / Qwen3.5 (#28208) DevVexusandClaude Opus 5 2026-09-07 02:12:50 -05:00
• b74f590eaf ggml-cuda: fix divergent barrier in f16 flash attention (#27870) Siavash Norouzi 2026-09-06 23:23:21 -07:00
• 992cb503cd ggml: allow backend inputs to not create another split (#28387) Aman Gupta 2026-09-07 14:10:40 +08:00
• 9ac8c408a3 vulkan: rms_norm fusion opportunities (#28024) Jeff Bolz 2026-09-07 01:08:28 -05:00
• 2092353c8b ci : add container image checking and tagging (wip) (#28394) Daniel Bevenius 2026-09-07 07:23:39 +02:00
• 8fe90e1fbf vulkan: add TQ1_0 support (mm, mat-vec, mat-vec-id, dequant, get_rows) (#27765) Anjielon 2026-09-07 06:35:30 +02:00
• 465e49b9ce convert : add --fuse-qkv flag to fuse Q/K/V into QKV during HF-to-GGUF conversion (#22780) PikaPikachu 2026-09-07 00:47:05 +08:00
• 5fdfa62829 models : fix GDN normalization from max to rsqrt (#28068) Daniel HanandGeorgi Gerganov 2026-09-06 09:46:21 -07:00
• 3ad1ba7336 [Model] Support for Spark2_5ForCausalLM implementation (#27868) 3 people 2026-09-06 23:43:58 +08:00
• d03efa5d53 opencl: properly choose weights pack for q4_K, q5_K mul_mat (#28402) lhez 2026-09-06 08:33:08 -07:00
• 73a43d1f69 cuda: fixes races in mmid and mmf (#28475) Aman Gupta 2026-09-06 19:45:01 +08:00
• 9e0e220594 grammar : fix max repetition threshold (#28469) Aldehir Rojas 2026-09-06 03:59:10 -05:00
• 0afb805b19 ui: Improve Chat Messages rendering performance (#28460) Aleksander Grygier 2026-09-06 10:52:40 +02:00
• 7620399f58 common: add --log-jsonl (#28437) Xuan-Son Nguyen 2026-09-06 08:21:22 +02:00
• c457e3bf7f ui : embed assets directly with CMake (#28445) Adrien Gallouët 2026-09-06 07:49:39 +02:00
• 971595d669 metal : add remaining fa-vec tunings for M2 Max (#28458) Niklas Wenzel 2026-09-06 07:37:01 +02:00
• 74a7c897f0 Github: limit blank issues to maintainers (#28435) Johannes Gäßler 2026-09-05 22:42:35 +02:00
• 6a1a922d26 metal : fix memory leak in early return (#28399) Niklas Wenzel 2026-09-05 12:19:47 +02:00
• 4d9176092d sycl : fix test-backend-ops CI break && restore Kronecker product FWHT support (#28016) (#28254) Jingxin (Philip) Li 2026-09-05 10:37:12 +08:00
• cd8cdf397d sycl: attribute device allocations by site (GGML_SYCL_MEMTRACE) (#27631) Nick Farrell 2026-09-05 12:36:02 +10:00
• 427291b5b3 metal : add remaining fa-vec tunings for M3 (#28396) Isaac 2026-09-05 00:08:34 +05:30
• 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) Hongqiang Wang 2026-09-04 10:12:26 -07:00
• 4acf4a4cb8 opencl: add Adreno xmem SDPA path (#26331) yzyyzyhhhandhappyyzy 2026-09-05 01:12:05 +08:00
• 8b4b3558f1 ci : move more jobs to ccache-buckets (#28375) Sigbjørn Skjæret 2026-09-04 15:50:33 +02:00