| 2026-08-15 |
Alessandro... | vendor: update BoringSSL to 0.20260813.0 (#27099) upstream/latest |
commit | commitdiff | tree |
| 2026-08-15 |
Alessandro... | vendor : update cpp-httplib to 0.53.1 (#27103) |
commit | commitdiff | tree |
| 2026-08-15 |
Eric Zhang | common: support --models-dir loading MTP assistant... |
commit | commitdiff | tree |
| 2026-08-15 |
Xuan-Son Nguyen | fix: check gguf array type before reading (#27075) |
commit | commitdiff | tree |
| 2026-08-15 |
Jiang, Fish | vulkan: add SHMEM_STRIDE_PAD/APPLY_SLM_A_RESHAPE for... |
commit | commitdiff | tree |
| 2026-08-15 |
Fathi Boudra | common: migrate the deprecated --mmap/--no-mmap to... |
commit | commitdiff | tree |
| 2026-08-15 |
Masato Nakasaka | fixed indent |
commit | commitdiff | tree |
| 2026-08-15 |
Masato Nakasaka | Fixed gating logic for problematic Intel driver version |
commit | commitdiff | tree |
| 2026-08-14 |
Hemanth Battu | mtmd: fix Granite4 Vision image sequence assembly ... upstream/0.0.10438 |
commit | commitdiff | tree |
| 2026-08-14 |
fairydreaming | model : add support for MiniMaxText01ForCausalLM and... |
commit | commitdiff | tree |
| 2026-08-14 |
Xuan-Son Nguyen | mtmd, common: various fixes (#27071) |
commit | commitdiff | tree |
| 2026-08-14 |
0 | jinja : fix quadratic cost in gather_string_parts ... |
commit | commitdiff | tree |
| 2026-08-14 |
Andy Williams | chat : pass reasoning_effort to template |
commit | commitdiff | tree |
| 2026-08-14 |
Georgi Gerganov | sync : ggml |
commit | commitdiff | tree |
| 2026-08-14 |
Georgi Gerganov | ggml : bump version to 0.20.0 (ggml/1584) |
commit | commitdiff | tree |
| 2026-08-14 |
lnigam | ggml : recurrent state rollback for ggml_ssm_scan ... |
commit | commitdiff | tree |
| 2026-08-14 |
Georgi Gerganov | llama : allow virtual igpu devices (#26953) |
commit | commitdiff | tree |
| 2026-08-14 |
Xuan-Son Nguyen | server: allow accessing /metrics and /slots during... |
commit | commitdiff | tree |
| 2026-08-14 |
Jim Wu | tests : replace personal home directory paths with... |
commit | commitdiff | tree |
| 2026-08-14 |
Titaniumtown | sycl: fuse mul_mat(gate) + mul_mat(up) + GLU for q4_K... |
commit | commitdiff | tree |
| 2026-08-14 |
Mendy Berger | ggml: force single thread on wasi (#25686) |
commit | commitdiff | tree |
| 2026-08-14 |
Titaniumtown | sycl: fuse the gated-delta-net state writeback cpy... |
commit | commitdiff | tree |
| 2026-08-14 |
Daniel Bevenius | dflash : clarify output logging of target_layer_ids... |
commit | commitdiff | tree |
| 2026-08-13 |
Niklas Wenzel | common: apply CPU parameters across tools (#27026) |
commit | commitdiff | tree |
| 2026-08-13 |
Aleksander... | ui: Refactor data-attrs constants, enum for bool string... |
commit | commitdiff | tree |
| 2026-08-13 |
Aleksander... | refactor: Naming (#27001) |
commit | commitdiff | tree |
| 2026-08-13 |
Ilya | ui: fix VITE_PUBLIC_SERVER variable reading (#24845) |
commit | commitdiff | tree |
| 2026-08-13 |
Zijun Yu | OpenVINO: Qwen3.5, memory optimization, and test-recurr... |
commit | commitdiff | tree |
| 2026-08-13 |
Neo Zhang | [SYCL] Support host pinned mem to improve SYCL Host... |
commit | commitdiff | tree |
| 2026-08-13 |
Aldehir Rojas | chat : fix LFM2 tool call arg name prefix ambiguity... |
commit | commitdiff | tree |
| 2026-08-13 |
Emanuil Rusev | server : serve index.html with no-cache (#27006) |
commit | commitdiff | tree |
| 2026-08-13 |
Sigbjørn Skjæret | spec : auto-detect mtp draft model type (#27005) |
commit | commitdiff | tree |
| 2026-08-13 |
Georgi Gerganov | metal : add TQ2_0 support (#26980) |
commit | commitdiff | tree |
| 2026-08-13 |
aic0d3r | common : auto-detect spec type from draft GGUF metadata... |
commit | commitdiff | tree |
| 2026-08-13 |
Ruixiang Wang | spec: enable backend sampling for both dflash & dspark... |
commit | commitdiff | tree |
| 2026-08-13 |
jinzihao | ggml-cpu/ops: vectorize flash-attention V-cache F16... |
commit | commitdiff | tree |
| 2026-08-13 |
Ian Faust | sycl: remove separate fp32 type promotion in gemm non... |
commit | commitdiff | tree |
| 2026-08-13 |
Titaniumtown | sycl: fuse UNARY(silu|sigmoid|softplus) + MUL (#26411) |
commit | commitdiff | tree |
| 2026-08-13 |
Todd Malsbary | sycl : Add DMMV ESIMD Q3_K kernel (#26251) |
commit | commitdiff | tree |
| 2026-08-13 |
Neo Zhang | sycl : enhance concat to support Q4_0, Q4_1, Q5_0,... |
commit | commitdiff | tree |
| 2026-08-13 |
Xuan-Son Nguyen | server: refactor + correctness fixes for metrics (... |
commit | commitdiff | tree |
| 2026-08-13 |
Jim Wu | ggml-hip : remove -funsafe-math-optimizations (#26696) |
commit | commitdiff | tree |
| 2026-08-13 |
Aleksander... | ui: Clean up contexts, remove prop drilling from Chat... |
commit | commitdiff | tree |
| 2026-08-13 |
Aleksander... | ui: Move `styles/` to `$lib` scope (#26950) |
commit | commitdiff | tree |
| 2026-08-13 |
Aleksander... | ui: Stores architecture improvements (#26910) |
commit | commitdiff | tree |
| 2026-08-13 |
Aleksander... | refactor: Clean up UI types (#26909) |
commit | commitdiff | tree |
| 2026-08-13 |
Georgi Gerganov | ggml : fix arm builds, unused var (#26991) |
commit | commitdiff | tree |
| 2026-08-13 |
Aleksander... | ui: Constants refactor (#26908) |
commit | commitdiff | tree |
| 2026-08-12 |
Johnathan Craig... | common: add system-level config file (#26118) |
commit | commitdiff | tree |
| 2026-08-12 |
Eve | ci: fix thread sanitizer + remove ccache (#26927) |
commit | commitdiff | tree |
| 2026-08-12 |
Sigbjørn Skjæret | ci : disable ubuntu-rocm (#26969) |
commit | commitdiff | tree |
| 2026-08-12 |
Sigbjørn Skjæret | disable rocm cache (#26962) |
commit | commitdiff | tree |
| 2026-08-12 |
Daniel Bevenius | cmake : introduce semantic versioning (#26839) |
commit | commitdiff | tree |
| 2026-08-12 |
HarrisonSec | gguf : harden loader against malformed tensor dims... |
commit | commitdiff | tree |
| 2026-08-12 |
Jonathan Clohessy | kleidiai: Add runtime feature detection mechanism for... |
commit | commitdiff | tree |
| 2026-08-12 |
Sigbjørn Skjæret | model : disallow integer dflash sliding_window_pattern... |
commit | commitdiff | tree |
| 2026-08-12 |
Georgi Gerganov | sync : ggml |
commit | commitdiff | tree |
| 2026-08-12 |
Daniel Bevenius | cmake : add config version support (ggml/1582) |
commit | commitdiff | tree |
| 2026-08-12 |
Chipmunk | server : support slot save/restore with media inputs... |
commit | commitdiff | tree |
| 2026-08-12 |
parabelboi | ui: add read_media tool (#25877) |
commit | commitdiff | tree |
| 2026-08-12 |
Hongqiang Wang | opencl: default FA c8 cluster width to 16 on X1E (... |
commit | commitdiff | tree |
| 2026-08-12 |
Georgi Gerganov | tests : update speculative params (#26925) |
commit | commitdiff | tree |
| 2026-08-12 |
michaeltrabalka... | vulkan: add TQ2_0 (ternary) support (#25850) |
commit | commitdiff | tree |
| 2026-08-12 |
Oğuzhan Akkaya | wavtokenizer-dec : bound posnet/convnext block_count... |
commit | commitdiff | tree |
| 2026-08-12 |
Wang Zhiyu | convert : handle per_layer_config in Gemma4 (transforme... |
commit | commitdiff | tree |
| 2026-08-12 |
lhez | opencl: use flat mv q5_k when weight exceeds image1d_bu... |
commit | commitdiff | tree |
| 2026-08-11 |
ruanslv | chat : fix muse-glimmer detection of tool calls after... |
commit | commitdiff | tree |
| 2026-08-11 |
Sigbjørn Skjæret | ci : add missing release check (#26923) |
commit | commitdiff | tree |
| 2026-08-11 |
Rafail Giavrimis | CUDA: only disable CUDA graphs when mul_mat_id actually... |
commit | commitdiff | tree |
| 2026-08-11 |
0 | cuda : add warp-per-row wkv7 kernel for single-token... |
commit | commitdiff | tree |
| 2026-08-11 |
Georgi Gerganov | spec : update speculative-simple (#26904) |
commit | commitdiff | tree |
| 2026-08-11 |
Aldehir Rojas | chat : tighten bare function parsing for Qwen models... |
commit | commitdiff | tree |
| 2026-08-11 |
Sigbjørn Skjæret | ci : add windows-rocm to check-release (#26897) |
commit | commitdiff | tree |
| 2026-08-11 |
Bartowski | imatrix.cpp: Move finite check and only check touched... |
commit | commitdiff | tree |
| 2026-08-11 |
Niklas Wenzel | requirements: use stable torch packages on s390x (... |
commit | commitdiff | tree |
| 2026-08-11 |
ynankani | convert : keep quantization scales for nemotron --mtp... |
commit | commitdiff | tree |
| 2026-08-11 |
lnigam | Dflash support for nemotron-3.5 (#26905) |
commit | commitdiff | tree |
| 2026-08-11 |
Xuan-Son Nguyen | mtmd: support pocket-tts (#26871) |
commit | commitdiff | tree |
| 2026-08-11 |
Tom Tan | ui: fix context gauge for single-model usage (#25738) |
commit | commitdiff | tree |
| 2026-08-11 |
uvos | ci: hip-quality-check: update vgpr spill ignore list... |
commit | commitdiff | tree |
| 2026-08-11 |
Daniel Bevenius | model-conversion : use save_output_data for causual... |
commit | commitdiff | tree |
| 2026-08-11 |
Georgi Gerganov | tests : fix running server tests on windows (#26889) |
commit | commitdiff | tree |
| 2026-08-11 |
Ruben Ortlam | llama: add default load-mode auto, which avoids mmap... |
commit | commitdiff | tree |
| 2026-08-11 |
Georgi Gerganov | tests : clean-up server test, use `tests.sh` in ci... |
commit | commitdiff | tree |
| 2026-08-11 |
Jim Wu | tests : disable backend sampler hip multi output (... |
commit | commitdiff | tree |
| 2026-08-11 |
Junmo Kim | model : fix SWA not being enabled for EXAONE 4.5 (... |
commit | commitdiff | tree |
| 2026-08-11 |
Aldehir Rojas | common/peg : suppress incomplete escape sequences ... |
commit | commitdiff | tree |
| 2026-08-11 |
Masashi Yoshimura | ggml-webgpu: fix CI errors from #25025 and #25262 ... |
commit | commitdiff | tree |
| 2026-08-10 |
Gaurav Garg | Address review comment of PR 25532 (#26852) |
commit | commitdiff | tree |
| 2026-08-10 |
Hongqiang Wang | opencl: transpose the K tile in local memory for FA... |
commit | commitdiff | tree |
| 2026-08-10 |
Mario Limonciello | ci : target ROCm 7.14 for build and release (#25775) |
commit | commitdiff | tree |
| 2026-08-10 |
Gaurav Garg | llama : support multi-output backend sampling (#25532) |
commit | commitdiff | tree |
| 2026-08-10 |
Hitesh Chopra | ggml-cpu : fix CPU affinity mask being ignored on Andro... |
commit | commitdiff | tree |
| 2026-08-10 |
Yash Raj Pandey | ggml : require contiguous src for ROLL on CUDA and... |
commit | commitdiff | tree |
| 2026-08-10 |
Pascal | ui: UI/chat form follow ups (#26743) |
commit | commitdiff | tree |
| 2026-08-10 |
Sigbjørn Skjæret | ci : don't specify python version in server-sanitize... |
commit | commitdiff | tree |
| 2026-08-10 |
Pascal | server: add more tool isolation support (ssh remote... |
commit | commitdiff | tree |
| 2026-08-10 |
Pedro Cuenca | model: Muse Glimmer Support (#26841) |
commit | commitdiff | tree |
| 2026-08-10 |
Guido Imperiale | chat : Align Laguna-S-2.1 chat template to huggingface... |
commit | commitdiff | tree |
| 2026-08-10 |
Pascal | vendor: sync subprocess.h and drop local patches (... |
commit | commitdiff | tree |
| next |
overview / pkg / ggml / sources / llama.cpp / shortlog