| 2026-06-19 |
Xuan-Son Nguyen | server: add --agent arg, remove redundant webui naming... |
commit | commitdiff | tree |
| 2026-06-19 |
Aldehir Rojas | docker : build the UI (#24794) |
commit | commitdiff | tree |
| 2026-06-19 |
Xuan-Son Nguyen | mtmd: several bug fixes (#24784) |
commit | commitdiff | tree |
| 2026-06-19 |
Ruixiang Wang | spec: support eagle3 for qwen3.5 & 3.6 (#24593) |
commit | commitdiff | tree |
| 2026-06-19 |
Xuan-Son Nguyen | server: fix non-bound n_discard value (ctx shifting... |
commit | commitdiff | tree |
| 2026-06-19 |
Georgi Gerganov | sync : ggml |
commit | commitdiff | tree |
| 2026-06-19 |
Georgi Gerganov | ggml : bump version to 0.15.2 (ggml/1548) |
commit | commitdiff | tree |
| 2026-06-19 |
Georgi Gerganov | pi : remove docs from system prompt (#24791) |
commit | commitdiff | tree |
| 2026-06-19 |
Georgi Gerganov | server : consolidate slot selection into get_available_... |
commit | commitdiff | tree |
| 2026-06-19 |
shalinib-ibm | ggml-cpu: support K tails in power10 Q8/Q4 MMA matmul... |
commit | commitdiff | tree |
| 2026-06-18 |
Xuan-Son Nguyen | mtmd: add batching support for internvl (#24775) |
commit | commitdiff | tree |
| 2026-06-18 |
Pascal | Ggml/cuda col2im 1d (#24417) |
commit | commitdiff | tree |
| 2026-06-18 |
Reguna | server: add "X-Accel-Buffering": "no" header to streami... |
commit | commitdiff | tree |
| 2026-06-18 |
Xuan-Son Nguyen | mtmd: add batching for mtmd-cli, add video tests (... |
commit | commitdiff | tree |
| 2026-06-18 |
o7si | cmake : fix ui build with read-only source (#24752) |
commit | commitdiff | tree |
| 2026-06-18 |
Xuan-Son Nguyen | mtmd: refactor llava-uhd overview image handling (alway... |
commit | commitdiff | tree |
| 2026-06-18 |
Max Krasnyansky | hexagon: support for op-trace (fine-grain tracing... |
commit | commitdiff | tree |
| 2026-06-18 |
Kangjia Gao | docs: fix export-lora --lora-scaled syntax [no release... |
commit | commitdiff | tree |
| 2026-06-18 |
Xuan-Son Nguyen | server: (router) fix stopping_thread potentially hang... |
commit | commitdiff | tree |
| 2026-06-18 |
Xuan-Son Nguyen | server: add "schema" and validation (#24150) |
commit | commitdiff | tree |
| 2026-06-18 |
Aarni Koskela | server : add last-5-seconds generation speed display... |
commit | commitdiff | tree |
| 2026-06-18 |
Amos Wong | ui: provide touch accessible model selection UI (#24604) |
commit | commitdiff | tree |
| 2026-06-18 |
Anuj Attri | server : return HTTP 400 on invalid grammar (#24144... |
commit | commitdiff | tree |
| 2026-06-18 |
Xuan-Son Nguyen | server: (router) rework -hf preset repo (#24739) |
commit | commitdiff | tree |
| 2026-06-18 |
Xuan-Son Nguyen | server: fix router args not being forwarded to child... |
commit | commitdiff | tree |
| 2026-06-18 |
Xuan-Son Nguyen | mtmd: refactor preprocessor, add mtmd_image_preproc_out... |
commit | commitdiff | tree |
| 2026-06-18 |
Neo Zhang | [SYCL] rename GGML_SYCL_SUPPORT_LEVEL_ZERO (#24719) |
commit | commitdiff | tree |
| 2026-06-18 |
Neo Zhang | sycl : support MUL_MAT and OUT_PROD with Q1_0 (#24721) |
commit | commitdiff | tree |
| 2026-06-18 |
Adrien Gallouët | app : enable self-update only when built with llama... |
commit | commitdiff | tree |
| 2026-06-18 |
Sigbjørn Skjæret | ci : fix check-release message parsing (#24751) |
commit | commitdiff | tree |
| 2026-06-18 |
Neo Zhang | [SYCL] support OPs: conv_2d, conv_2d_dw, conv2d_transpo... |
commit | commitdiff | tree |
| 2026-06-18 |
Aleksander... | ui: Update code formatting command in pre-commit hook... |
commit | commitdiff | tree |
| 2026-06-18 |
Ravi Panchumarthy | ci : fix Windows x64 (OpenVINO) release link (#24731) |
commit | commitdiff | tree |
| 2026-06-18 |
Georgi Gerganov | metal : check for BF16 support in concat kernel (#24747) |
commit | commitdiff | tree |
| 2026-06-17 |
Xuan-Son Nguyen | mtmd: llava_uhd should no longer use batch dim (#24732) |
commit | commitdiff | tree |
| 2026-06-17 |
shalinib-ibm | ggml-cpu: Conditionally enable power11 backend based... |
commit | commitdiff | tree |
| 2026-06-17 |
Georgi Gerganov | metal : implement rope_back operator (#24725) |
commit | commitdiff | tree |
| 2026-06-17 |
Georgi Gerganov | metal : add f16 and bf16 support for concat operator... |
commit | commitdiff | tree |
| 2026-06-17 |
Xuan-Son Nguyen | server: (router) add model management API (#23976) |
commit | commitdiff | tree |
| 2026-06-17 |
Dev-iL | llama : skip main_gpu validation when no devices are... |
commit | commitdiff | tree |
| 2026-06-17 |
Ruixiang Wang | spec: fix segfault error on long prompts for eagle3... |
commit | commitdiff | tree |
| 2026-06-17 |
Neo Zhang | [SYCL] add dev2dev memcpy by SYCL API (#24476) |
commit | commitdiff | tree |
| 2026-06-17 |
Neo Zhang | [SYCL] Add conv_3d (#24691) |
commit | commitdiff | tree |
| 2026-06-17 |
Julien Chaumond | webui: export conversations as jsonl (#24688) |
commit | commitdiff | tree |
| 2026-06-17 |
Winston Ma | vulkan: record actual memory properties during buffer... |
commit | commitdiff | tree |
| 2026-06-17 |
Ruben Ortlam | Revert "cuda: reset cuda context after reading memory... |
commit | commitdiff | tree |
| 2026-06-17 |
kononnable | ci: fix vulkan docker images (#24595) |
commit | commitdiff | tree |
| 2026-06-17 |
Harapan Rachman | UI : fix SSE transport detection and routing through... |
commit | commitdiff | tree |
| 2026-06-17 |
lhez | opencl: optimize mul_mat_f16_f32_l4 for decode (#24504) |
commit | commitdiff | tree |
| 2026-06-17 |
Max Krasnyansky | common: update logging to enforce max_capacity and... |
commit | commitdiff | tree |
| 2026-06-17 |
Zijun Yu | openvino: OV 2026.2, context-shift, Q5_1 support, gemma... |
commit | commitdiff | tree |
| 2026-06-17 |
Neo Zhang | sycl : Enable to support fp16 by OPs: SQR, SQRT, LOG... |
commit | commitdiff | tree |
| 2026-06-17 |
Alexey Kopytko | SYCL: fix use-after-free bug with async memcpy in MoE... |
commit | commitdiff | tree |
| 2026-06-17 |
Francois Dugast | sycl: Add optional USM system allocations (#22526) |
commit | commitdiff | tree |
| 2026-06-16 |
Alessandro... | vendor : update BoringSSL to 0.20260616.0 (#24693) |
commit | commitdiff | tree |
| 2026-06-16 |
Pascal | ui: add source toggle to mermaid and svg blocks (#24652) |
commit | commitdiff | tree |
| 2026-06-16 |
Oliver Simons | Fix and restrict NVFP4 edge-cases in llama-graph (... |
commit | commitdiff | tree |
| 2026-06-16 |
Ruixiang Wang | spec: add backend sampling support for eagle3 (#24655) |
commit | commitdiff | tree |
| 2026-06-16 |
Winston Ma | vulkan: prefer host-visible memory buffers on UMA devic... |
commit | commitdiff | tree |
| 2026-06-16 |
Jeff Bolz | vulkan: Support gated_delta_net with S_v=16 (#24581) |
commit | commitdiff | tree |
| 2026-06-16 |
Ruixiang Wang | spec: add spec metrics mean acceptance length and accep... |
commit | commitdiff | tree |
| 2026-06-16 |
Adrien Gallouët | bench : add --offline (#24511) |
commit | commitdiff | tree |
| 2026-06-16 |
Frosty40 | sycl: support reordered Q4_K/Q5_K/Q6_K MoE MUL_MAT_ID... |
commit | commitdiff | tree |
| 2026-06-16 |
Neo Zhang | [SYCL] Support OP EXPM1, support all UT cases of FLOOR... |
commit | commitdiff | tree |
| 2026-06-16 |
Todd Malsbary | sycl : Make GGML_SYCL_F16=ON the default (#23996) |
commit | commitdiff | tree |
| 2026-06-16 |
Pascal | vulkan: add col2im_1d op (#24425) |
commit | commitdiff | tree |
| 2026-06-15 |
Tarek Dakhran | chat : fix LFM2 tool-call parsing double-escaping ... |
commit | commitdiff | tree |
| 2026-06-15 |
Xuan-Son Nguyen | mtmd: fix miscounting n_tokens (#24656) |
commit | commitdiff | tree |
| 2026-06-15 |
Piotr Wilkin... | chat: include full unparsed prompt in debug (#24650) |
commit | commitdiff | tree |
| 2026-06-15 |
Julien Jerphanion | docs: Add instructions to install `llama.cpp` from... |
commit | commitdiff | tree |
| 2026-06-15 |
Pascal | chat: harden peg-native tool call parsing (#24329) |
commit | commitdiff | tree |
| 2026-06-15 |
Piotr Wilkin... | chat: fix an "oldie but goodie" grammar generator bug... |
commit | commitdiff | tree |
| 2026-06-15 |
Georgi Gerganov | mtmd : add post-decode callback (#24645) |
commit | commitdiff | tree |
| 2026-06-15 |
Jeff Bolz | vulkan: support more CONCAT types (#24579) |
commit | commitdiff | tree |
| 2026-06-15 |
Andrei | wasm : fix fallback symbol collision (#24639) |
commit | commitdiff | tree |
| 2026-06-15 |
Katostrofik | SYCL: use native subgroup size for K-quant DMMV (#21700) |
commit | commitdiff | tree |
| 2026-06-15 |
someoneinjd | sycl: fix soft_max_f32 max reduction (#24451) |
commit | commitdiff | tree |
| 2026-06-15 |
Neo Zhang | sycl : fix reorder function; add fp32/fp16 in build... |
commit | commitdiff | tree |
| 2026-06-15 |
Neo Zhang | sycl : enhance set_rows to support q1_0, mxfp4, nvfp4... |
commit | commitdiff | tree |
| 2026-06-15 |
Neo Zhang | [SYCL] add to support pool_1d, move pool_1d/2d code... |
commit | commitdiff | tree |
| 2026-06-15 |
Alexey Kopytko | [SYCL]: Remove per-allocation Level Zero runtime checks... |
commit | commitdiff | tree |
| 2026-06-15 |
Georgi Gerganov | metal : add repeat bf16 (#24638) |
commit | commitdiff | tree |
| 2026-06-15 |
Piotr Wilkin... | chat: fix whitespace problems once and for all (#24624) |
commit | commitdiff | tree |
| 2026-06-15 |
Pascal | UI/svg block rendering (#24080) |
commit | commitdiff | tree |
| 2026-06-15 |
leonardHONG | CUDA: only support F32/F16 for GGML_OP_REPEAT (#24533) |
commit | commitdiff | tree |
| 2026-06-15 |
Masashi Yoshimura | ggml-webgpu: improve i-quants mul_mat performance and... |
commit | commitdiff | tree |
| 2026-06-14 |
Sigbjørn Skjæret | convert : fix lora base model arch retrieval (#24621) |
commit | commitdiff | tree |
| 2026-06-14 |
franitel | fix(ui): render thinking/reasoning block content as... |
commit | commitdiff | tree |
| 2026-06-14 |
Nicolas Mowen | ui: Add HEIC/HEIF image support (#24137) |
commit | commitdiff | tree |
| 2026-06-14 |
Piotr Wilkin... | chat: add dedicated Cohere2MoE (North Code) parser... |
commit | commitdiff | tree |
| 2026-06-14 |
Mohammad Athar | docs : fix typos in CUDA-FEDORA.md and grammars/README... |
commit | commitdiff | tree |
| 2026-06-14 |
Alexander Batischev | docker: specify registry to simplify Podman builds... |
commit | commitdiff | tree |
| 2026-06-14 |
Pascal | UI/mobile keyboard and pwa popup fixes (#24610) |
commit | commitdiff | tree |
| 2026-06-14 |
Amos Wong | ui : fix ui clipping in mobile due to incorrect height... |
commit | commitdiff | tree |
| 2026-06-14 |
Sigbjørn Skjæret | jinja : add count/d/e filter aliases (#24606) |
commit | commitdiff | tree |
| 2026-06-14 |
Michael Wand | cli : fix not copying preserved tokens (#24258) |
commit | commitdiff | tree |
| 2026-06-14 |
Bartowski | Add cohere2moe to llama-vocab for TINY_AYA (#24601) |
commit | commitdiff | tree |
| 2026-06-14 |
Sigbjørn Skjæret | ci : use CUDA label for cuda backend (#24594) |
commit | commitdiff | tree |
| 2026-06-14 |
Sigbjørn Skjæret | add sycl to check-release (#24583) |
commit | commitdiff | tree |
| 2026-06-13 |
Aldehir Rojas | ui : fix llama-ui-embed crash when no asset dir is... |
commit | commitdiff | tree |
| next |
overview / pkg / ggml / sources / llama.cpp / shortlog