| 2026-06-26 |
QuantiusBenignus | examples : fix argument flag for min speech duration... |
commit | commitdiff | tree |
| 2026-06-23 |
Daniel Bevenius | examples : update model names in parakeet-cli README... |
commit | commitdiff | tree |
| 2026-06-23 |
Nicky Mouha | Fix pkgconfig configuration (Nix build failure) (#3894) |
commit | commitdiff | tree |
| 2026-06-22 |
Naitik Shah | include parakeet in build-xcframework.sh (#3899) |
commit | commitdiff | tree |
| 2026-06-19 |
Georgi Gerganov | talk-llama : sync llama.cpp |
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 |
shalinib-ibm | ggml-cpu: support K tails in power10 Q8/Q4 MMA matmul... |
commit | commitdiff | tree |
| 2026-06-19 |
Pascal | Ggml/cuda col2im 1d (llama/24417) |
commit | commitdiff | tree |
| 2026-06-19 |
Max Krasnyansky | hexagon: support for op-trace (fine-grain tracing of... |
commit | commitdiff | tree |
| 2026-06-19 |
Neo Zhang | rename GGML_SYCL_SUPPORT_LEVEL_ZERO (llama/24719) |
commit | commitdiff | tree |
| 2026-06-19 |
Neo Zhang | sycl : support MUL_MAT and OUT_PROD with Q1_0 (llama... |
commit | commitdiff | tree |
| 2026-06-19 |
Neo Zhang | support OPs: conv_2d, conv_2d_dw, conv2d_transpose... |
commit | commitdiff | tree |
| 2026-06-19 |
Georgi Gerganov | metal : check for BF16 support in concat kernel (llama... |
commit | commitdiff | tree |
| 2026-06-19 |
shalinib-ibm | ggml-cpu: Conditionally enable power11 backend based... |
commit | commitdiff | tree |
| 2026-06-19 |
Georgi Gerganov | metal : implement rope_back operator (llama/24725) |
commit | commitdiff | tree |
| 2026-06-19 |
Georgi Gerganov | metal : add f16 and bf16 support for concat operator... |
commit | commitdiff | tree |
| 2026-06-19 |
Neo Zhang | add dev2dev memcpy by SYCL API (llama/24476) |
commit | commitdiff | tree |
| 2026-06-19 |
Neo Zhang | Add conv_3d (llama/24691) |
commit | commitdiff | tree |
| 2026-06-19 |
Winston Ma | vulkan: record actual memory properties during buffer... |
commit | commitdiff | tree |
| 2026-06-19 |
Ruben Ortlam | Revert "cuda: reset cuda context after reading memory... |
commit | commitdiff | tree |
| 2026-06-19 |
kononnable | ci: fix vulkan docker images (llama/24595) |
commit | commitdiff | tree |
| 2026-06-19 |
lhez | opencl: optimize mul_mat_f16_f32_l4 for decode (llama... |
commit | commitdiff | tree |
| 2026-06-19 |
Zijun Yu | openvino: OV 2026.2, context-shift, Q5_1 support, gemma... |
commit | commitdiff | tree |
| 2026-06-19 |
Neo Zhang | sycl : Enable to support fp16 by OPs: SQR, SQRT, LOG... |
commit | commitdiff | tree |
| 2026-06-19 |
Alexey Kopytko | SYCL: fix use-after-free bug with async memcpy in MoE... |
commit | commitdiff | tree |
| 2026-06-19 |
Francois Dugast | sycl: Add optional USM system allocations (llama/22526) |
commit | commitdiff | tree |
| 2026-06-19 |
Winston Ma | vulkan: prefer host-visible memory buffers on UMA devic... |
commit | commitdiff | tree |
| 2026-06-19 |
Jeff Bolz | vulkan: Support gated_delta_net with S_v=16 (llama... |
commit | commitdiff | tree |
| 2026-06-19 |
Frosty40 | sycl: support reordered Q4_K/Q5_K/Q6_K MoE MUL_MAT_ID... |
commit | commitdiff | tree |
| 2026-06-19 |
Neo Zhang | Support OP EXPM1, support all UT cases of FLOOR, TRUNC... |
commit | commitdiff | tree |
| 2026-06-19 |
Pascal | vulkan: add col2im_1d op (llama/24425) |
commit | commitdiff | tree |
| 2026-06-19 |
Jeff Bolz | vulkan: support more CONCAT types (llama/24579) |
commit | commitdiff | tree |
| 2026-06-19 |
Andrei | wasm : fix fallback symbol collision (llama/24639) |
commit | commitdiff | tree |
| 2026-06-19 |
Katostrofik | SYCL: use native subgroup size for K-quant DMMV (llama... |
commit | commitdiff | tree |
| 2026-06-19 |
someoneinjd | sycl: fix soft_max_f32 max reduction (llama/24451) |
commit | commitdiff | tree |
| 2026-06-19 |
Neo Zhang | sycl : fix reorder function; add fp32/fp16 in build... |
commit | commitdiff | tree |
| 2026-06-19 |
Neo Zhang | sycl : enhance set_rows to support q1_0, mxfp4, nvfp4... |
commit | commitdiff | tree |
| 2026-06-19 |
Neo Zhang | add to support pool_1d, move pool_1d/2d code to pool... |
commit | commitdiff | tree |
| 2026-06-19 |
Alexey Kopytko | Remove per-allocation Level Zero runtime checks (llama... |
commit | commitdiff | tree |
| 2026-06-19 |
Georgi Gerganov | metal : add repeat bf16 (llama/24638) |
commit | commitdiff | tree |
| 2026-06-19 |
leonardHONG | CUDA: only support F32/F16 for GGML_OP_REPEAT (llama... |
commit | commitdiff | tree |
| 2026-06-19 |
Masashi Yoshimura | ggml-webgpu: improve i-quants mul_mat performance and... |
commit | commitdiff | tree |
| 2026-06-19 |
Jeff Bolz | vulkan: support non-contig unary/glu ops (llama/24215) |
commit | commitdiff | tree |
| 2026-06-19 |
Ruben Ortlam | vulkan: add pipeline barriers for memcpy read operation... |
commit | commitdiff | tree |
| 2026-06-19 |
Daniel Bevenius | release : v1.9.1 (#3892) |
commit | commitdiff | tree |
| 2026-06-18 |
Daniel Bevenius | ci : add GGML_NATIVE=OFF and GGML_BMI2=OFF to windows... |
commit | commitdiff | tree |
| 2026-06-17 |
Daniel Bevenius | release : v1.9.0 (#3886) |
commit | commitdiff | tree |
| 2026-06-17 |
KITAITI Makoto | ruby : add support for Parakeet (#3885) |
commit | commitdiff | tree |
| 2026-06-16 |
Daniel Bevenius | parakeet : add support for NVIDIA Parakeet (#3735) |
commit | commitdiff | tree |
| 2026-06-16 |
Daniel Bevenius | ci : only trigger release jobs for tags (#3883) |
commit | commitdiff | tree |
| 2026-06-16 |
Daniel Bevenius | release : v1.8.7 (#3881) |
commit | commitdiff | tree |
| 2026-06-16 |
Rum Nguyen | cli : add --version flag (#3878) |
commit | commitdiff | tree |
| 2026-06-15 |
Georgi Gerganov | talk-llama : sync llama.cpp |
commit | commitdiff | tree |
| 2026-06-15 |
Georgi Gerganov | sync : ggml |
commit | commitdiff | tree |
| 2026-06-15 |
Georgi Gerganov | ggml : bump version to 0.15.1 (ggml/1541) |
commit | commitdiff | tree |
| 2026-06-15 |
ZihaoMu | ggml: support concat for scalar types at cuda backend... |
commit | commitdiff | tree |
| 2026-06-15 |
shaofeiqi | opencl: add q5_0/q5_1 gemm and gemv kernels for Adreno... |
commit | commitdiff | tree |
| 2026-06-15 |
Jeff Bolz | vulkan: ifdef eMesaHoneykrisp (build fix) (llama/24479) |
commit | commitdiff | tree |
| 2026-06-15 |
Georgi Gerganov | ggml : bump version to 0.15.0 (ggml/1539) |
commit | commitdiff | tree |
| 2026-06-15 |
Winston Ma | vulkan: add fast path for contiguous buffer transfers... |
commit | commitdiff | tree |
| 2026-06-15 |
Kevin Liu | vulkan: use medium matmul tile on Asahi Linux (llama... |
commit | commitdiff | tree |
| 2026-06-15 |
Gaurav Garg | Remove padding and multiple D2D copies for MTP (llama... |
commit | commitdiff | tree |
| 2026-06-15 |
Oliver Simons | CUDA: Fix ssm_scan_f32 data-races (llama/24360) |
commit | commitdiff | tree |
| 2026-06-15 |
Jeff Bolz | vulkan: reduce iq1 shared memory usage for mul_mm ... |
commit | commitdiff | tree |
| 2026-06-15 |
Ruben Ortlam | vulkan: add `v_dot2_f32_f16` support in matrix-matrix... |
commit | commitdiff | tree |
| 2026-06-15 |
Pascal | ggml : add GGML_OP_COL2IM_1D (llama/24206) |
commit | commitdiff | tree |
| 2026-06-15 |
Yash Raj Pandey | ggml-cpu : fix rms_norm_back wrong output under in... |
commit | commitdiff | tree |
| 2026-06-15 |
ravel7524 | Remove case for GGML_TYPE_Q4_K in mvvq.cu (llama/23528) |
commit | commitdiff | tree |
| 2026-06-15 |
Reese Levine | ggml-webgpu: Add clang-format job (llama/24308) |
commit | commitdiff | tree |
| 2026-06-15 |
Masashi Yoshimura | ggml-webgpu: Improve prefill speeds for k-quants +... |
commit | commitdiff | tree |
| 2026-06-15 |
Nikhil Jain | Handle buffer overlap / buffer aliasing for concat... |
commit | commitdiff | tree |
| 2026-06-15 |
Nikhil Jain | Implement 2D workgroups for scale, binary, and unary... |
commit | commitdiff | tree |
| 2026-06-15 |
Jeff Bolz | vulkan: Use cm2 decode_vector for mul_mat_id B matrix... |
commit | commitdiff | tree |
| 2026-06-15 |
Ruben Ortlam | cuda: reset cuda context after reading memory size... |
commit | commitdiff | tree |
| 2026-06-09 |
Daniel Bevenius | ci : pin github actions to commit sha's (#3865) |
commit | commitdiff | tree |
| 2026-06-09 |
Christopher... | coreml : fix --quantize crash for mlprogram format... |
commit | commitdiff | tree |
| 2026-06-08 |
Georgi Gerganov | talk-llama : sync llama.cpp |
commit | commitdiff | tree |
| 2026-06-08 |
Georgi Gerganov | sync : ggml |
commit | commitdiff | tree |
| 2026-06-08 |
Georgi Gerganov | ggml : bump version to 0.14.0 (ggml/1533) |
commit | commitdiff | tree |
| 2026-06-08 |
Georgi Gerganov | sync : ggml |
commit | commitdiff | tree |
| 2026-06-08 |
Harkirat Gill | HIP: add gfx1152 and gfx1153 to RDNA3.5 (llama/24129) |
commit | commitdiff | tree |
| 2026-06-08 |
Xuan-Son Nguyen | metal : fix im2col 1D case (audio models) (llama/24220) |
commit | commitdiff | tree |
| 2026-06-08 |
Ruben Ortlam | vulkan: check coopmat2 features before reporting suppor... |
commit | commitdiff | tree |
| 2026-06-08 |
lhez | opencl: improve get_rows, cpy, concat and q6_k flat... |
commit | commitdiff | tree |
| 2026-06-08 |
Ruben Ortlam | vulkan: add fwht support for Intel with shmem reduction... |
commit | commitdiff | tree |
| 2026-06-08 |
Charles Xu | kleidiai : dynamic chunck-based scheduling for hybrid... |
commit | commitdiff | tree |
| 2026-06-08 |
Oliver Simons | CUDA: enroll mul_mat_vec_q_moe into pdl (llama/24087) |
commit | commitdiff | tree |
| 2026-06-08 |
Mason Milburn | sycl : port multi-column MMVQ from CUDA backend (llama... |
commit | commitdiff | tree |
| 2026-06-08 |
Kartik Sirohi | ggml: vectorize ggml_vec_dot_q4_1_q8_1 with WASM SIMD12... |
commit | commitdiff | tree |
| 2026-06-08 |
Georgi Gerganov | metal : reduce rset heartbeat from 500ms -> 5ms (llama... |
commit | commitdiff | tree |
| 2026-06-08 |
Reese Levine | ggml-webgpu: FlashAttention refactor + standardize... |
commit | commitdiff | tree |
| 2026-06-08 |
rehan-10xengineer | ggml-cpu: extend RVV quantization vec dot to higher... |
commit | commitdiff | tree |
| 2026-06-08 |
Andreas Kieslinger | Avoid PDL race conditions by disabling __restrict__... |
commit | commitdiff | tree |
| 2026-06-08 |
Charles Xu | ggml-cpu: use runtime SVE width in FWHT (llama/24059) |
commit | commitdiff | tree |
| 2026-06-08 |
Aman Gupta | cuda: reserve space for quantize kv-cache at startup... |
commit | commitdiff | tree |
| 2026-06-08 |
lhez | opencl: use flat variants of q4_K and q6_K gemv for... |
commit | commitdiff | tree |
| 2026-06-08 |
Max Krasnyansky | hexagon: profiler output fix and script updates (llama... |
commit | commitdiff | tree |
| 2026-06-08 |
Max Krasnyansky | hexagon: MUL_MAT, MUL_MAT_ID, FLASH_ATTN and GDN cleanu... |
commit | commitdiff | tree |
| 2026-06-08 |
Todor Boinovski | hexagon: add gelu_quick (llama/24007) |
commit | commitdiff | tree |
| next |
overview / pkg / ggml / sources / whisper.cpp / shortlog