Commit Graph

Select branches

Hide Pull Requests

master

Mono Color

• e8023568d0 convert: Fix Gemma 4 Unified conversion (#24118) Pedro Cuenca 2026-06-04 15:21:38 +02:00
• 4c51309617 ggml: vectorize ggml_vec_dot_q4_1_q8_1 with WASM SIMD128 (#22209) Kartik Sirohi 2026-06-04 18:42:38 +05:30
• 6f3a9f3dee server: avoid unnecessary checkpoint restore when new tokens are present (#24110) Yongyue SunandGeorgi Gerganov 2026-06-04 21:09:01 +08:00
• a121232fdc agents: refactor, include more guidelines (#24111) Xuan-Son Nguyen 2026-06-04 13:40:23 +02:00
• 4586479852 webui: fix tool selector toggle/counter, key tools by stable identity (#24065) Pascal 2026-06-04 13:09:49 +02:00
• 4d742877b2 build : use umbrella Headers directory for XCFramework module map (#23974) Gerard Martinez 2026-06-04 03:58:25 -07:00
• 0066404085 server : add header to tools/server/server-http.h (#24089) A B 2026-06-04 05:14:46 -05:00
• 7ac5a4225e cmake: skip cvector-generator and export-lora when CPU backend is disabled (#24053) Andrea Richiardi 2026-06-04 04:13:19 -06:00
• e3ba22d6cc fix(mtmd): handle Gemma 4 audio projector embedding size (#24091) AndreiandXuan Son Nguyen 2026-06-04 02:51:23 -07:00
• 6ddc9430b1 readme : add status badges (#24104) Georgi Gerganov 2026-06-04 10:58:13 +03:00
• 65ef50a0a4 tests : refactor test-save-load-state to accept token input (#24073) Georgi Gerganov 2026-06-04 08:06:36 +03:00
• 3d1998634e metal : reduce rset heartbeat from 500ms -> 5ms (#24074) Georgi Gerganov 2026-06-04 08:05:32 +03:00
• e8c54893f2 ggml-webgpu: FlashAttention refactor + standardize quantization support (#23834) Reese Levine 2026-06-03 22:05:04 -07:00
• 3c7450cee1 ggml-cpu: extend RVV quantization vec dot to higher VLENs (#22754) 3 people 2026-06-04 10:03:40 +05:00
• f478f1b6d7 sycl : Improve SYCL doc (#23025) Todd Malsbary 2026-06-03 22:02:54 -07:00
• 94a220cd67 mtmd: fix Gemma 4 unified FPE (#24088) Andrei 2026-06-03 12:51:18 -07:00
• 166fe29492 qwen35: use post-norm hidden state for MTP (#24025) Aman Gupta 2026-06-04 01:29:09 +08:00
• c8d6a00636 mtmd: enable non-causal vision for gemma 4 unified (#24082) Xuan-Son Nguyen 2026-06-03 19:05:17 +02:00
• a731805ced mtmd, model: allow skip build_vit() (#24077) Xuan-Son Nguyen 2026-06-03 17:10:35 +02:00
• ee4cf705bb ui: Mermaid Diagrams in chat + interactive preview (#24032) Aleksander Grygier 2026-06-03 16:55:36 +02:00
• 9e58d4d692 Avoid PDL race conditions by disabling __restrict__ when PDL is used (#24030) Andreas KieslingerandOliver Simons 2026-06-03 13:56:42 +02:00
• 3571fa5435 ggml-cpu: use runtime SVE width in FWHT (#24059) Charles Xu 2026-06-03 12:45:10 +02:00
• f8f0a47a55 cuda: reserve space for quantize kv-cache at startup (#23907) Aman GuptaandJohannes Gäßler 2026-06-03 18:39:59 +08:00
• 06938ac129 tests : add support for qwen3 SSM archs (#24031) Georgi Gerganov 2026-06-03 10:15:27 +03:00
• d545a2a993 update BoringSSL to 0.20260526.0 (#23794) Alessandro de Oliveira Faria (A.K.A.CABELO) 2026-06-03 02:42:58 -03:00
• 4da6370d43 ci : disable ccache for msvc windows release jobs (#23911) Georgi Gerganov 2026-06-03 08:05:21 +03:00
• e3666269f9 arg : removed unecesary mmproj download when users pass --no-mmproj (#23425) Ryan Mangeno 2026-06-02 22:04:46 -07:00
• 63e66fdd23 opencl: use flat variants of q4_K and q6_K gemv for very large M (#24006) lhez 2026-06-02 14:16:17 -07:00
• 5c394fdc8b hexagon: profiler output fix and script updates (#24042) Max Krasnyansky 2026-06-02 14:08:29 -07:00
• 4fb16eccce model: add Mellum architecture (#23966) Mikhail PodvitskiiandSigbjørn Skjæret 2026-06-02 21:11:12 +02:00
• bfb4308b05 model : support granite multilingual embeddings R2 (ibm-granite/granite-embedding-{97,311}m-multilingual-r2) (#22716) Hans Florian 2026-06-02 11:55:11 -04:00
• 2187e00337 StepFun 3.5 MTP (#23274) Piotr Wilkin (ilintar)andSigbjørn Skjæret 2026-06-02 17:44:35 +02:00
• 0b7154066e common : fix state save in common_prompt_batch_decode (#23468) Daniel Beveniusandfairydreaming 2026-06-02 15:44:15 +02:00
• 60130d18f9 server: add SSE ping interval (#24013) Xuan-Son Nguyen 2026-06-02 14:14:55 +02:00
• a468b89018 ci : reduce self-hosted server workflow jobs (#24012) Georgi Gerganov 2026-06-02 13:17:59 +03:00
• d5ab0834ab docs : update HOWTO-add-model.md (#23883) Mikhail PodvitskiiandSigbjørn Skjæret 2026-06-02 11:40:22 +02:00
• 69cea5b669 ui: simplify network error handling (#23431) Marcos Del Sol Vives 2026-06-02 10:45:25 +02:00
• f8e67fc583 ui: Add Thinking mode toggle with reasoning effort levels + improvements for Chat Form Add Action UI (#23434) Aleksander Grygier 2026-06-02 10:23:19 +02:00
• 2365315955 kv-cache : SWA checkpoints store only non-masked cells (#23981) Georgi Gerganov 2026-06-02 11:06:29 +03:00
• f7a0777a5c convert : support Step3.7-Flash (#23845) forforever73andSigbjørn Skjæret 2026-06-02 15:54:49 +08:00
• 4f3a4beb8d llama : deprecate llama_set_warmup (#24009) Georgi GerganovandDaniel Bevenius 2026-06-02 10:30:38 +03:00
• 8f7f3bf141 hexagon: MUL_MAT, MUL_MAT_ID, FLASH_ATTN and GDN cleanup and optimizations for latest models (#23989) Max Krasnyansky 2026-06-01 23:40:08 -07:00
• d178a11818 hexagon: add gelu_quick (#24007) Todor Boinovski 2026-06-01 23:19:07 -07:00
• 354ebac8cb server: real-time reasoning interruption via control endpoint (#23971) PascalandAleksander Grygier 2026-06-02 07:26:20 +02:00
• 1fd5f48037 clean up unused variables warnings (#23975) Anav Prasad 2026-06-01 19:38:37 -07:00
• 210a6570ce opencl: fix compiler warnings for non-adreno path (#23922) lhez 2026-06-01 19:15:09 -07:00
• b8275a8acc revert to using global_invocation_id for cpy shader (#23955) Masashi Yoshimura 2026-06-02 08:59:06 +09:00
• 5dcb711666 speculative : fix n_outputs_max and remove draft-simple auto-enable (#23988) Georgi Gerganov 2026-06-01 22:26:58 +03:00
• 5aa3a64596 nix : add nix-nodejs facilities to build Web UI (#23846) Christian Hoener zu Siederdissen 2026-06-01 20:01:26 +02:00
• 27d9ed8397 opencl: add basic support for q5_0 and q5_1 (#23548) shaofeiqiandLi He 2026-06-01 10:06:50 -07:00
• 335abed17d vendor : update cpp-httplib to 0.46.1 (#23980) Adrien Gallouët 2026-06-01 18:40:10 +02:00
• de6f727aae llama: limit max outputs of llama_context (#23861) Aman Gupta 2026-06-01 23:01:38 +08:00
• 95b8b8ec1a metal: template GLU kernels to support f16/f32 (#23882) Shrivas Shankar 2026-06-01 07:40:28 -05:00
• 55ac0909e5 vulkan: don't hold the device mutex while compiling pipelines (#23641) Jeff Bolz 2026-06-01 07:04:01 -05:00
• bef69f1306 vulkan: reduce host memory lock contention (#23376) Winston Ma 2026-06-01 20:03:32 +08:00
• 5aba5364d9 vocab: add normalizer.lowercase support to WPM (#23899) o7si 2026-06-01 19:26:47 +08:00
• 8e6fff84de TP: quantized KV cache support (#23792) Johannes Gäßler 2026-06-01 12:30:10 +02:00
• 02a57017f6 security : disable private disclosures (#23963) Georgi Gerganov 2026-06-01 13:14:12 +03:00
• 48b88c3b00 model: Add EXAONE 4.5 implementations (#21733) Junwon HwangandLG-AI-EXAONE 2026-06-01 18:48:53 +09:00
• 19620004f5 vulkan: Block-load Q3_K/Q6_K block data and subtract on 32b ints (#23056) Matt Corallo 2026-06-01 09:46:48 +00:00
• f8c0a19d46 vulkan: Removed unused functions (#23175) Winston Ma 2026-06-01 17:46:23 +08:00
• 5254a7994d common : support manually triggering the reasoning budget end sequence (#23949) Aldehir Rojas 2026-06-01 05:37:11 -04:00
• e22b0de60d ci : add missing Linux label to cpu-x64-high-perf runner (#23958) Georgi Gerganov 2026-06-01 10:39:59 +03:00
• a51142497a [SYCL] Support Q4_1, Q5_0, Q5_1 in Flash-attention (#23812) Neo Zhang 2026-06-01 14:53:53 +08:00
• 4162522688 [SYCL] Add more types in GET_ROWS OP (#23710) Neo Zhang 2026-06-01 14:53:04 +08:00
• 44e211cecf sycl : Optimize Q3_K mul_mat by reorder (#23725) Neo Zhang 2026-06-01 14:50:55 +08:00
• af6528e6df ci: remove redundant or duplicate jobs (#23927) Eve 2026-06-01 03:32:17 +00:00
• 6f165c1c64 server : handle If-None-Match weak ETags (#23916) Eric Zhang 2026-06-01 05:21:08 +08:00
• 399739d5c5 ci : limit trigger paths for the CPU workflow (#23938) Georgi Gerganov 2026-05-31 19:02:47 +03:00
• d4c8e2c29c vocab : add tokenizer support for jina-embeddings-v2-base-zh (#18756) o7siandSigbjørn Skjæret 2026-05-31 18:37:35 +08:00
• 3292da09f6 ui: fix ETag truncation with MSVC compiler (#23917) Eric Zhang 2026-05-31 17:21:23 +08:00
• e6123e2080 docs : update ZenDNN docs for Q8 support (#23791) Vladislavandplotnikov.v10 2026-05-31 11:26:42 +03:00
• 22cadc1944 llama: only use one iGPU device by default (#23897) Ruben Ortlam 2026-05-31 08:17:47 +02:00
• d749821db3 webui: add custom CSS injection via config (#23904) PascalandAleksander Grygier 2026-05-30 23:49:31 +02:00
• aa46bda89b Support -fa auto in llama-bench (#23714) Gaurav Garg 2026-05-31 02:03:57 +05:30
• d6588daa80 opencl: support bf16 by converting to f16 (#23839) lhez 2026-05-30 10:17:47 -07:00
• d38d50e7ff ui: exclude generated build dirs from prettier and eslint so lint errors stop being masked (#23910) Pascal 2026-05-30 16:50:54 +02:00
• 8b0e0db606 TP: fix granularity for Qwen 3.5/3.6 + 3 GPUs (#23843) Johannes Gäßler 2026-05-30 15:48:00 +02:00
• 2d9b7c8e98 metal : restore im2col implementation for large kernels (#23901) Georgi Gerganov 2026-05-30 15:26:13 +03:00
• e674b1279b test: (test-llama-archs) log the config name first (#23885) Xuan-Son Nguyen 2026-05-30 12:22:38 +02:00
• 4c4e91b799 ci : update ios-xcode release job to macos-26 (#23906) Georgi Gerganov 2026-05-30 13:21:46 +03:00
• d48a56effb ggml : add some lsx support (#23798) Jinyang He 2026-05-30 16:53:26 +08:00
• 6e093b80ea vulkan: add Flash Attention support for BFloat16 KV cache (#23420) Ruben Ortlam 2026-05-30 10:39:31 +02:00
• 337528571d ci : fix s390x release job (#23898) Georgi Gerganov 2026-05-30 09:21:38 +03:00
• d4204b03a5 ci : clear cache instead of "no timestamp" keys + fix macos (#23895) Georgi Gerganov 2026-05-30 08:52:30 +03:00
• 1738129bee llama : do not skip iGPU when only RPC devices are present (#23868) Radoslav Gerganov 2026-05-30 07:48:22 +03:00
• 0821c5fcfd server: in SSE mode, send HTTP headers when slot starts (#23884) Xuan-Son Nguyen 2026-05-30 00:06:29 +02:00
• 151f3a98e9 ggml-webgpu: Check earlier for WebGPU required features (#23879) Reese Levine 2026-05-29 14:16:05 -07:00
• b22da25889 ggml-webgpu: add q4_0/q8_0 SET_ROWS (#23760) Reese Levine 2026-05-29 14:14:11 -07:00
• 689a9a470e server-bench : add speed-bench for speculative decoding benchmarking (#23869) Ruixiang Wang 2026-05-29 23:09:47 +02:00
• 5a46b46acd app: add llama update self updater (#23865) Pascal 2026-05-29 23:02:40 +02:00
• 22d66b567e ui: handle audio/vnd.wave as audio WAV file (#23754) ValdikSS 2026-05-29 22:41:35 +03:00
• 2084434e66 vocab : support tokenizer for LFM2.5-8B-A1B (#23826) Tarek Dakhran 2026-05-29 20:25:43 +02:00
• 764f1e64a1 graph : ensure DS32 kq_mask_lid is F32 (#23864) Sigbjørn Skjæret 2026-05-29 19:55:14 +02:00
• b5f52280fb server: remove obsolete scripts (#23870) Xuan-Son Nguyen 2026-05-29 19:47:30 +02:00
• dc71236b6c ci : update macos release to use macos-26 runner (#23878) Georgi Gerganov 2026-05-29 20:41:57 +03:00
• 06d26dfdff download: add option to skip_download (#23059) Xuan-Son Nguyen 2026-05-29 16:30:55 +02:00
• da3f990a47 mtmd: Add DeepSeekOCR 2 Support (#20975) Saba FallahandXuan-Son Nguyen 2026-05-29 16:13:51 +02:00
• 6ed481eea4 CUDA: Check PTX version on host side to guard PDL dispatch (#23530) Oliver SimonsandJohannes Gäßler 2026-05-29 12:28:18 +02:00
• cb47092b00 server: bump timeout to 3600s (#23842) Xuan-Son Nguyen 2026-05-29 10:23:17 +02:00