| 2025-12-05 |
Reese Levine | ggml webgpu: unary op suppport, code refactoring, ops... |
commit | commitdiff | tree |
| 2025-12-05 |
Jeff Bolz | vulkan: enable mmvq for q2_k on NVIDIA (#17675) |
commit | commitdiff | tree |
| 2025-12-05 |
Jeff Bolz | vulkan: set all memory allocations to high priority... |
commit | commitdiff | tree |
| 2025-12-05 |
Georgi Gerganov | rpc : fix alloc size logic (#17116) |
commit | commitdiff | tree |
| 2025-12-05 |
Georgi Gerganov | metal : add residency sets keep-alive heartbeat (#17766) |
commit | commitdiff | tree |
| 2025-12-05 |
Johannes Gäßler | HIP : fix RDNA4 build (#17792) |
commit | commitdiff | tree |
| 2025-12-05 |
Pascal | fix: prevent segfault in tokenizer on highly repetitive... |
commit | commitdiff | tree |
| 2025-12-05 |
Adrien Gallouët | ci : fix winget workflow (#17790) |
commit | commitdiff | tree |
| 2025-12-05 |
shalinib-ibm | Q4/Q8 Tiled Gemm Optimization. (#16999) |
commit | commitdiff | tree |
| 2025-12-05 |
Piotr Wilkin... | Add pwilkin to CODEOWNERS for chat files (#17789) |
commit | commitdiff | tree |
| 2025-12-05 |
Johannes Gäßler | CUDA: fix FA VKQ accumulator overflow (#17746) |
commit | commitdiff | tree |
| 2025-12-05 |
Jiacheng (Jason... | HIP: enable WMMA-MMQ INT kernels for RDNA 3 (#17576) |
commit | commitdiff | tree |
| 2025-12-05 |
Sigbjørn Skjæret | ci : transform release binary root dir in tar to llama... |
commit | commitdiff | tree |
| 2025-12-04 |
Gabe Goodhart | docs : update ops.md (Metal, BLAS) (#17768) |
commit | commitdiff | tree |
| 2025-12-04 |
Piotr Wilkin... | Add support for CUMSUM and TRI for CUDA. (#17584) |
commit | commitdiff | tree |
| 2025-12-04 |
Gabe Goodhart | metal: TRI, FILL, EXPM1, SOFTPLUS (#16623) |
commit | commitdiff | tree |
| 2025-12-04 |
Xuan-Son Nguyen | server: strip content-length header on proxy (#17734) |
commit | commitdiff | tree |
| 2025-12-04 |
Xuan-Son Nguyen | server: move msg diffs tracking to HTTP thread (#17740) |
commit | commitdiff | tree |
| 2025-12-04 |
Daniel Bevenius | examples : add missing code block end marker [no ci... |
commit | commitdiff | tree |
| 2025-12-04 |
Daniel Bevenius | common : skip model validation when --help is requested... |
commit | commitdiff | tree |
| 2025-12-04 |
Alberto Cabrera... | ggml-cpu : remove asserts always evaluating to false... |
commit | commitdiff | tree |
| 2025-12-04 |
SmartestWashingMachine | convert: use existing local chat_template if mistral... |
commit | commitdiff | tree |
| 2025-12-04 |
Adrien Gallouët | cmake : simplify build info detection using standard... |
commit | commitdiff | tree |
| 2025-12-04 |
Sigbjørn Skjæret | ci : disable ggml-ci-x64-amd-* (#17753) |
commit | commitdiff | tree |
| 2025-12-04 |
Adrien Gallouët | common: use native MultiByteToWideChar (#17738) |
commit | commitdiff | tree |
| 2025-12-04 |
Georgi Gerganov | metal : use params per pipeline instance (#17739) |
commit | commitdiff | tree |
| 2025-12-04 |
Georgi Gerganov | llama : fix sanity checks during quantization (#17721) |
commit | commitdiff | tree |
| 2025-12-04 |
Adrien Gallouët | build : move _WIN32_WINNT definition to headers (#17736) |
commit | commitdiff | tree |
| 2025-12-04 |
Jeff Bolz | build: enable parallel builds in msbuild using MTT... |
commit | commitdiff | tree |
| 2025-12-03 |
Herman Semenoff | ggml-cpu: remove duplicate conditional check 'iid'... |
commit | commitdiff | tree |
| 2025-12-03 |
Piotr Wilkin... | Add a couple of file types to the text section (#17670) |
commit | commitdiff | tree |
| 2025-12-03 |
SmartestWashingMachine | convert : support latest mistral-common (fix conversion... |
commit | commitdiff | tree |
| 2025-12-03 |
Aleksander... | Use OpenAI-compatible `/v1/models` endpoint by default... |
commit | commitdiff | tree |
| 2025-12-03 |
Andika Wasisto | webui: Fix zero pasteLongTextToFileLen to disable conve... |
commit | commitdiff | tree |
| 2025-12-03 |
Johannes Gäßler | CUDA: generalized (mma) FA, add Volta support (#17505) |
commit | commitdiff | tree |
| 2025-12-03 |
Georgi Gerganov | chat : reserve memory in compute_diffs and improve... |
commit | commitdiff | tree |
| 2025-12-03 |
Pascal | server: add router multi-model tests (#17704) (#17722) |
commit | commitdiff | tree |
| 2025-12-03 |
Adrien Gallouët | server : fix bad fmt, size() is a size_type (#17735) |
commit | commitdiff | tree |
| 2025-12-03 |
Adrien Gallouët | cmake: explicitly link against crypt32 on non-MSVC... |
commit | commitdiff | tree |
| 2025-12-03 |
Georgi Gerganov | metal : fix data race in pipeline library (#17731) |
commit | commitdiff | tree |
| 2025-12-03 |
jiahao su | ci : remove the build of openeuler-cann in release... |
commit | commitdiff | tree |
| 2025-12-03 |
Aldehir Rojas | common : introduce composable PEG parser combinators... |
commit | commitdiff | tree |
| 2025-12-03 |
Pascal | server: fix duplicate HTTP headers in multiple models... |
commit | commitdiff | tree |
| 2025-12-03 |
Reese Levine | ggml webgpu: add support for emscripten builds (#17184) |
commit | commitdiff | tree |
| 2025-12-03 |
Sigbjørn Skjæret | ci : move release details to the top visible by default... |
commit | commitdiff | tree |
| 2025-12-03 |
Herman Semenoff | ggml, llama : use defaulted constructors/destructors... |
commit | commitdiff | tree |
| 2025-12-03 |
Marcos Del... | build: document how to compile with Vulkan using Debian... |
commit | commitdiff | tree |
| 2025-12-02 |
Xuan-Son Nguyen | server: add --media-path for local media files (#17697) |
commit | commitdiff | tree |
| 2025-12-02 |
Xuan-Son Nguyen | mtmd: fix --no-warmup (#17695) |
commit | commitdiff | tree |
| 2025-12-02 |
Ali Tariq | ci : RVV1.0 builds with tests (#16682) |
commit | commitdiff | tree |
| 2025-12-02 |
Jeff Bolz | vulkan: Reduce temporary memory usage for TOP_K (#17623) |
commit | commitdiff | tree |
| 2025-12-02 |
xiaobing318 | cmake : add utf8 compilation options for msvc (#17682) |
commit | commitdiff | tree |
| 2025-12-02 |
Chad Voegele | Server: Change Invalid Schema from Server Error (500... |
commit | commitdiff | tree |
| 2025-12-02 |
Adrien Gallouët | ggml : use svcntb() for SVE vector length detection... |
commit | commitdiff | tree |
| 2025-12-02 |
TianHao324 | CANN: Disable Ger operator of OUT_PROD on 310p device... |
commit | commitdiff | tree |
| 2025-12-02 |
Daniel Bevenius | ggml : remove redundant n_copies check when setting... |
commit | commitdiff | tree |
| 2025-12-02 |
Eric Curtin | codeowners : remove ericcurtin (#17658) |
commit | commitdiff | tree |
| 2025-12-02 |
Adrien Gallouët | llama : fix signed comparison warning on FreeBSD (... |
commit | commitdiff | tree |
| 2025-12-02 |
Xuan-Son Nguyen | convert: add error message for mistral3 quantized weigh... |
commit | commitdiff | tree |
| 2025-12-02 |
Xuan-Son Nguyen | server: remove default "gpt-3.5-turbo" model name ... |
commit | commitdiff | tree |
| 2025-12-02 |
senhtry | server: fixing naming conflict res_error in server... |
commit | commitdiff | tree |
| 2025-12-02 |
Xuan-Son Nguyen | server: explicitly set exec path when create new instan... |
commit | commitdiff | tree |
| 2025-12-02 |
Adrien Gallouët | ci : skip winget update when not in ggml-org (#17465) |
commit | commitdiff | tree |
| 2025-12-02 |
Adrien Gallouët | ggml : add fallback definition for HWCAP2_SVE2 (#17683) |
commit | commitdiff | tree |
| 2025-12-02 |
Aleksander... | Add context info to server error (#17663) |
commit | commitdiff | tree |
| 2025-12-02 |
Aman Gupta | ggml-cuda: reorder only relevant nodes (#17639) |
commit | commitdiff | tree |
| 2025-12-02 |
Aaron Teo | release: fix duplicate libs, store symbolic links ... |
commit | commitdiff | tree |
| 2025-12-02 |
Neo Zhang Jianyu | enhance argsort for UT (#17573) |
commit | commitdiff | tree |
| 2025-12-01 |
Piotr Wilkin... | Override SSM_A op for Qwen3 Next to reduce splits ... |
commit | commitdiff | tree |
| 2025-12-01 |
Jeff Bolz | ops.md: update vulkan support (#17661) |
commit | commitdiff | tree |
| 2025-12-01 |
Xuan-Son Nguyen | mtmd: add mtmd_context_params::warmup option (#17652) |
commit | commitdiff | tree |
| 2025-12-01 |
Gilad S. | fix: llama arch implementation (#17665) |
commit | commitdiff | tree |
| 2025-12-01 |
Xuan-Son Nguyen | server: introduce API for serving / loading / unloading... |
commit | commitdiff | tree |
| 2025-12-01 |
Xuan-Son Nguyen | common: improve verbosity level definitions (#17630) |
commit | commitdiff | tree |
| 2025-12-01 |
Xuan-Son Nguyen | model: support Ministral3 (#17644) |
commit | commitdiff | tree |
| 2025-12-01 |
Georgi Gerganov | metal : add FA head size 48 (#17619) |
commit | commitdiff | tree |
| 2025-12-01 |
Georgi Gerganov | ggml : extend the GGML_SCHED_NO_REALLOC debug logic... |
commit | commitdiff | tree |
| 2025-12-01 |
Aman Gupta | llama-graph: avoid expand_forward for fusion (#17633) |
commit | commitdiff | tree |
| 2025-11-30 |
Xuan-Son Nguyen | contributing: update guidelines for AI-generated code... |
commit | commitdiff | tree |
| 2025-11-30 |
Adrien Gallouët | cmake : add option to build and link LibreSSL (#17552) |
commit | commitdiff | tree |
| 2025-11-30 |
Tarek Dakhran | model: LFM2-VL fixes (#17577) |
commit | commitdiff | tree |
| 2025-11-30 |
Xuan-Son Nguyen | clip: fix nb calculation for qwen3-vl (#17594) |
commit | commitdiff | tree |
| 2025-11-30 |
Xuan-Son Nguyen | cli: add migration warning (#17620) |
commit | commitdiff | tree |
| 2025-11-30 |
Adrien Gallouët | common : throttle download progress output to reduce... |
commit | commitdiff | tree |
| 2025-11-30 |
Aaron Teo | common: add LLAMA_LOG_FILE env var (#17609) |
commit | commitdiff | tree |
| 2025-11-30 |
Gilad S. | ggml: fix: macOS build with `-DGGML_BACKEND_DL=ON`... |
commit | commitdiff | tree |
| 2025-11-30 |
ddh0 | common: update env var name (#17588) |
commit | commitdiff | tree |
| 2025-11-30 |
Aman Gupta | CUDA: add stream-based concurrency (#16991) |
commit | commitdiff | tree |
| 2025-11-30 |
Mahekk Shaikh | cuda : add error checking for cudaMemcpyAsync in... |
commit | commitdiff | tree |
| 2025-11-30 |
Acly | vulkan : fix FA mask load with bounds check (coopmat2... |
commit | commitdiff | tree |
| 2025-11-29 |
Xuan-Son Nguyen | server: move server-context to its own cpp|h (#17595) |
commit | commitdiff | tree |
| 2025-11-29 |
Haiyue Wang | server: explicitly set the function name in lambda... |
commit | commitdiff | tree |
| 2025-11-29 |
Igor Smirnov | common : fix json schema with '\' in literals (#17307) |
commit | commitdiff | tree |
| 2025-11-29 |
Neo Zhang | sycl : support to malloc memory on device more than... |
commit | commitdiff | tree |
| 2025-11-29 |
ixgbe | ggml: replace hwcap with riscv_hwprobe for RVV detectio... |
commit | commitdiff | tree |
| 2025-11-29 |
Ruben Ortlam | Vulkan: MMVQ Integer Dot K-Quant and MUL_MAT_ID support... |
commit | commitdiff | tree |
| 2025-11-29 |
Jeff Bolz | vulkan: improve topk perf for large k, fix overflow... |
commit | commitdiff | tree |
| 2025-11-28 |
Aleksei Nikiforov | gguf-py : fix passing non-native endian tensors (editor... |
commit | commitdiff | tree |
| 2025-11-28 |
DAN™ | common : move all common_chat_parse_* to chat-parser... |
commit | commitdiff | tree |
| 2025-11-28 |
o7si | server: fix: /metrics endpoint returning JSON-escaped... |
commit | commitdiff | tree |
| next |
overview / pkg / ggml / sources / llama.cpp / shortlog