| 2026-03-29 |
Georgi Gerganov | metal : add FA instantiations for HSK=512, HSV=512... |
commit | commitdiff | tree |
| 2026-03-29 |
Max Krasnyansky | hexagon: general DMA and Binary Op fixes for large... |
commit | commitdiff | tree |
| 2026-03-29 |
lhez | opencl: add q6_K gemm and gemv kernels for Adreno ... |
commit | commitdiff | tree |
| 2026-03-29 |
las7 | rpc : RCE patch (llama/20908) |
commit | commitdiff | tree |
| 2026-03-29 |
Rashid Ul Islam | metal: add CONV_3D (llama/19927) |
commit | commitdiff | tree |
| 2026-03-29 |
Chenguang Li | CANN: add RoPE cache preload before ACL graph capture... |
commit | commitdiff | tree |
| 2026-03-29 |
Dan Hoffman | fix(openvino): explicit memset in buffer_context alloca... |
commit | commitdiff | tree |
| 2026-03-29 |
shaofeiqi | opencl: add flattened Q4_K mv and general Q4_K mm ... |
commit | commitdiff | tree |
| 2026-03-29 |
Johannes Gäßler | CUDA: fix BF16 FA compilation (llama/20865) |
commit | commitdiff | tree |
| 2026-03-29 |
Neo Zhang | support bf16 and quantized type (llama/20803) |
commit | commitdiff | tree |
| 2026-03-29 |
Patrick Buckley | ggml-cuda: native bf16 flash attention for vec kernel... |
commit | commitdiff | tree |
| 2026-03-29 |
Gaurav Garg | Increase number of output elements per-thread block... |
commit | commitdiff | tree |
| 2026-03-29 |
y198 | fix(rpc): prevent division by zero in deserialize_tenso... |
commit | commitdiff | tree |
| 2026-03-29 |
Matt Corallo | Add shader count for Intel Arc Pro B60 (llama/20818) |
commit | commitdiff | tree |
| 2026-03-29 |
shalinib-ibm | ggml-cpu: add always_inline to tinyBLAS_PPC accumulator... |
commit | commitdiff | tree |
| 2026-03-29 |
Jeff Bolz | vulkan: change gated_delta_net to shard a column across... |
commit | commitdiff | tree |
| 2026-03-29 |
hipudding | CANN: add BF16 support for core operators (llama/20152) |
commit | commitdiff | tree |
| 2026-03-29 |
Sundaram krishnan | ggml: guard KleidiAI DOWNLOAD_EXTRACT_TIMESTAMP for... |
commit | commitdiff | tree |
| 2026-03-29 |
Rail Chabdarov | hip: Avoid compiler bug in RDNA code generation during... |
commit | commitdiff | tree |
| 2026-03-29 |
Yiwei Shao | hexagon: add Matrix Extensions (HMX) for Hexagon NPU... |
commit | commitdiff | tree |
| 2026-03-29 |
uvos | ci : add hip quality check (llama/20430) |
commit | commitdiff | tree |
| 2026-03-29 |
Reese Levine | ggml webgpu: ops support for qwen3.5 (SET, TRI_SOLVE... |
commit | commitdiff | tree |
| 2026-03-29 |
Eve | vulkan: dequantize iq4_xs 4 at a time (llama/20657) |
commit | commitdiff | tree |
| 2026-03-29 |
Charles Xu | cmake : fix build warning when kleidiai is enabled... |
commit | commitdiff | tree |
| 2026-03-29 |
Chenguang Li | CANN: handle in-place ROPE on non-contiguous f32 tensor... |
commit | commitdiff | tree |
| 2026-03-29 |
Masashi Yoshimura | ggml-webgpu: Update the `RMS_NORM` preprocessor and... |
commit | commitdiff | tree |
| 2026-03-29 |
Masashi Yoshimura | ggml-webgpu: Add supports for `DIAG` and `TRI` (llama... |
commit | commitdiff | tree |
| 2026-03-29 |
Chenguang Li | CANN: support flash attention for head dim not multiple... |
commit | commitdiff | tree |
| 2026-03-29 |
Reese Levine | Move to no timeout for WaitAny in graph submission... |
commit | commitdiff | tree |
| 2026-03-29 |
Shaw Nguyen | ggml-cpu/x86: fix unused changemask warning in repack... |
commit | commitdiff | tree |
| 2026-03-29 |
uvos | HIP : ignore return of hipMemAdvise [no ci] (llama... |
commit | commitdiff | tree |
| 2026-03-29 |
Krishna Sridhar | hexagon: add neg, exp, sigmoid, softplus ops, cont... |
commit | commitdiff | tree |
| 2026-03-29 |
Ruben Ortlam | vulkan: disable mmvq on Intel Windows driver (llama... |
commit | commitdiff | tree |
| 2026-03-29 |
Kevin Hannon | ggml-blas: set mkl threads from thread context (llama... |
commit | commitdiff | tree |
| 2026-03-29 |
Taimur Ahmad | ggml-cpu: fix RVV checks in quants and repacking (llama... |
commit | commitdiff | tree |
| 2026-03-29 |
Ruben Ortlam | vulkan: async and event fixes (llama/20518) |
commit | commitdiff | tree |
| 2026-03-29 |
Justin Bradford | kleidiai : fix MUL_MAT support for batched (3D) inputs... |
commit | commitdiff | tree |
| 2026-03-29 |
Ruben Ortlam | vulkan: allow graphics queue only through env var ... |
commit | commitdiff | tree |
| 2026-03-29 |
Neo Zhang | ehance UPSCALE to support all UT cases (llama/20637) |
commit | commitdiff | tree |
| 2026-03-29 |
Martin Klacer | kleidiai: add data type check to get_tensor_traits... |
commit | commitdiff | tree |
| 2026-03-29 |
Ruben Ortlam | vulkan: fix flash attention dot product precision ... |
commit | commitdiff | tree |
| 2026-03-29 |
Aman Gupta | CUDA: GDN hide memory latency (llama/20537) |
commit | commitdiff | tree |
| 2026-03-29 |
Sigbjørn Skjæret | sycl : fix for untransposed GDA recurrent state (llama... |
commit | commitdiff | tree |
| 2026-03-21 |
KITAITI Makoto | ruby : fix dangling pointers, memory leak, and SEGV... |
commit | commitdiff | tree |
| 2026-03-19 |
Georgi Gerganov | release : v1.8.4 upstream/1.8.4 |
commit | commitdiff | tree |
| 2026-03-18 |
Georgi Gerganov | ci : update workflows |
commit | commitdiff | tree |
| 2026-03-18 |
Georgi Gerganov | benches : update |
commit | commitdiff | tree |
| 2026-03-18 |
Georgi Gerganov | sync : ggml |
commit | commitdiff | tree |
| 2026-03-18 |
Georgi Gerganov | ggml : bump version to 0.9.8 (ggml/1442) |
commit | commitdiff | tree |
| 2026-03-18 |
Georgi Gerganov | ggml : restore ggml_type_sizef() to aboid major version... |
commit | commitdiff | tree |
| 2026-03-17 |
lohopupa | fix: VAD time mapping timestamp drift caused by overlap... |
commit | commitdiff | tree |
| 2026-03-16 |
Alan | go : handle EOF correctly in model download (#3671) |
commit | commitdiff | tree |
| 2026-03-16 |
Aiudadadadf | py : replace deprecated openvino-dev with openvino... |
commit | commitdiff | tree |
| 2026-03-16 |
Gaël James | examples : Allow max_len to be used for any output... |
commit | commitdiff | tree |
| 2026-03-16 |
Igor Loskutov | server: return proper HTTP status codes for error respo... |
commit | commitdiff | tree |
| 2026-03-16 |
Georgi Gerganov | ggml : try fix arm build (#0) |
commit | commitdiff | tree |
| 2026-03-16 |
Georgi Gerganov | talk-llama : sync llama.cpp |
commit | commitdiff | tree |
| 2026-03-16 |
Georgi Gerganov | sync : ggml |
commit | commitdiff | tree |
| 2026-03-16 |
David366AI | ggml : extend im2col f16 (ggml/1434) |
commit | commitdiff | tree |
| 2026-03-16 |
Georgi Gerganov | common : add nvfp4 (ggml/0) |
commit | commitdiff | tree |
| 2026-03-16 |
Johannes Gäßler | CUDA: limit number of FA stream-k CUDA blocks (llama... |
commit | commitdiff | tree |
| 2026-03-16 |
Pascal | ggml: avoid creating CUDA context during device init... |
commit | commitdiff | tree |
| 2026-03-16 |
MoonShadow | ggml/hip: fix APU compatibility - soft error handling... |
commit | commitdiff | tree |
| 2026-03-16 |
Bartowski | ggml : guard against sumq2 being 0 in IQ4_NL (llama... |
commit | commitdiff | tree |
| 2026-03-16 |
PikaPikachu | cuda : add RDNA4-specific MMVQ parameter table for... |
commit | commitdiff | tree |
| 2026-03-16 |
Ruben Ortlam | vulkan: use graphics queue on AMD (llama/20551) |
commit | commitdiff | tree |
| 2026-03-16 |
Georgi Gerganov | metal : add FA specialization for HSK = 320, HSV =... |
commit | commitdiff | tree |
| 2026-03-16 |
Max Krasnyansky | hexagon: Q4_0 and MXFP4 repack fixes (llama/20527) |
commit | commitdiff | tree |
| 2026-03-16 |
Neo Zhang | add op gated_delta_net (llama/20455) |
commit | commitdiff | tree |
| 2026-03-16 |
Adrien Gallouët | ggml : add native AVX512-FP16 support for F16 operation... |
commit | commitdiff | tree |
| 2026-03-16 |
Wallentri | Use fp32 in cuBLAS V100 to avoid overflows, env variabl... |
commit | commitdiff | tree |
| 2026-03-16 |
Zijun Yu | ggml : add OpenVINO backend (llama/15307) |
commit | commitdiff | tree |
| 2026-03-16 |
Rail Chabdarov | Fix data race in CUDA's "cpy" kernel (influences GGML... |
commit | commitdiff | tree |
| 2026-03-16 |
lhez | opencl: fix l2_norm (llama/20480) |
commit | commitdiff | tree |
| 2026-03-16 |
Georgi Gerganov | graph : remove redundant GDN state transposes (llama... |
commit | commitdiff | tree |
| 2026-03-16 |
rehan-10xengineer | ggml-cpu: add RVV vec dot kernels for quantization... |
commit | commitdiff | tree |
| 2026-03-16 |
Adrien Gallouët | ggml : fix typo gmml (llama/20512) |
commit | commitdiff | tree |
| 2026-03-16 |
Georgi Gerganov | metal : fix l2 norm scale (llama/20493) |
commit | commitdiff | tree |
| 2026-03-16 |
Georgi Gerganov | llama : disable graph reuse with pipeline parallelism... |
commit | commitdiff | tree |
| 2026-03-16 |
ProgenyAlpha | vulkan: add GATED_DELTA_NET op support (llama/20334) |
commit | commitdiff | tree |
| 2026-03-16 |
ProgenyAlpha | vulkan: fix SSM_CONV PP scaling with large ubatch sizes... |
commit | commitdiff | tree |
| 2026-03-16 |
Georgi Gerganov | sync : ggml |
commit | commitdiff | tree |
| 2026-03-16 |
Georgi Gerganov | metal : avoid divisions in bin kernel (llama/20426) |
commit | commitdiff | tree |
| 2026-03-16 |
Georgi Gerganov | sync : ggml |
commit | commitdiff | tree |
| 2026-03-16 |
Jeff Bolz | vulkan: fix l2_norm epsilon handling (llama/20350) |
commit | commitdiff | tree |
| 2026-03-16 |
Jeff Bolz | vulkan: fix OOB check in flash_attn_mask_opt (llama... |
commit | commitdiff | tree |
| 2026-03-16 |
Masato Nakasaka | vulkan: Fix ErrorOutOfHostMemory on Intel GPU when... |
commit | commitdiff | tree |
| 2026-03-16 |
lhez | opencl: use larger workgroup size for get_rows (llama... |
commit | commitdiff | tree |
| 2026-03-16 |
shaofeiqi | opencl: add cumsum op (llama/18981) |
commit | commitdiff | tree |
| 2026-03-16 |
uvos | hip: compile debug builds with -O2 on hip to avoid... |
commit | commitdiff | tree |
| 2026-03-16 |
Masashi Yoshimura | ggml-webgpu: Add supports for `GGML_OP_REPEAT` (llama... |
commit | commitdiff | tree |
| 2026-03-16 |
Georgi Gerganov | llama : enable chunked fused GDN path (llama/20340) |
commit | commitdiff | tree |
| 2026-03-16 |
Richard Davison | ggml : add NVFP4 quantization type support (llama/19769) |
commit | commitdiff | tree |
| 2026-03-16 |
Daniel Bevenius | llama : add support for Nemotron 3 Super (llama/20411) |
commit | commitdiff | tree |
| 2026-03-16 |
Georgi Gerganov | metal : fix capture_compute counter logic (llama/20410) |
commit | commitdiff | tree |
| 2026-03-16 |
Georgi Gerganov | metal : fix q5_k mul_mv register spill (llama/20399) |
commit | commitdiff | tree |
| 2026-03-16 |
Georgi Gerganov | metal : add env var to trigger graph capture (llama... |
commit | commitdiff | tree |
| 2026-03-16 |
uvos | ggml-cuda: gdn use shared mem for HIP (llama/20366) |
commit | commitdiff | tree |
| 2026-03-16 |
uvos | cuda/hip: fix loop unrolling in ssm-conv (llama/20369) |
commit | commitdiff | tree |
| 2026-03-16 |
Neo Zhang | fix op rope, add rope_back (llama/20293) |
commit | commitdiff | tree |
| next |
overview / pkg / ggml / sources / whisper.cpp / shortlog