Open Hub
Open Hub

 Settings |  Report Duplicate

0
I Use This!
Very High Activity

Commits : Listings

Analyzed about 2 hours ago. based on code collected about 20 hours ago.
Oct 03, 2025 — Oct 03, 2026
Commit Message Contributor Files Modified Lines Added Lines Removed Code Location Date
whisper : add check for ttype in whisper and parakeet (#4091)
Vincenzo Reina
More... 1 day ago
cli : fix incorrect error code when files are failing (#4080)
Vincenzo Reina
More... 5 days ago
ci : cover GGML_BACKEND_DL in ubuntu-22-clang-arm64 (#4047)
Abir Deol
More... 10 days ago
sync : ggml
Georgi Gerganov
More... 10 days ago
ggml : bump version to 0.25.1 (ggml/1637)
Georgi Gerganov
More... 11 days ago
CUDA: add a reserve to avoid spurious warning on older GCC builds (llama/29317)
Aman Gupta
More... 11 days ago
metal: add the missing f32 x bf16 mul_mv variants (llama/28741)
Pascal
More... 11 days ago
CUDA: enable sparse-fa for dsv4 prefill (again) (llama/29298)
Aman Gupta
More... 11 days ago
metal : key the fa-vec tuned table by family instead of SKU (llama/29075)
YiChen Lv
More... 11 days ago
whisper : add abort_callback on lang detection (#4077)
Vincenzo Reina
More... 11 days ago
sync : ggml
Georgi Gerganov
More... 11 days ago
ggml : bump version to 0.25.0 (ggml/1635)
Georgi Gerganov
More... 11 days ago
common : fix for two functions when top_k exceeds the vocabulary size. (ggml/1633)
Arianna Method
More... 11 days ago
sycl : fix compile warnings
Georgi Gerganov
More... 11 days ago
vulkan: add IQ4_XS MMQ/MMV matmul kernels (llama/28415)
Piotr Wilkin (ilintar)
More... 11 days ago
ggml-meta: resolve multi buffer views (llama/29266)
Ruben Ortlam
More... 11 days ago
cuda: top-k MoE should always fire (llama/28432)
Aman Gupta
More... 11 days ago
sycl : support new UT case for mul_mat_hadamard fp16 (llama/29218)
Neo Zhang
More... 11 days ago
sycl: extend MMVQ GLU fusion, add rms_norm+scale and ssm_conv+silu fusions (llama/28931)
Anant Shrivastava
More... 11 days ago
sycl : support op get_rows_back, only support fp32/fp16 (llama/25266)
Neo Zhang
More... 11 days ago
vulkan: hide internal symbols to prevent duplicate-dlopen state destruction (llama/29139)
Erik Winter
More... 11 days ago
hex-dma: introduce direct-mapped DMA cache that is better suited for HVX FA mask handling (llama/29282)
Max Krasnyansky
More... 11 days ago
HIP : optimize IQ2/IQ3 (`__vsub4` `__vcmpne4`) using SWAR (llama/27962)
Felix Ye
More... 11 days ago
opencl: add bin kernel `kernel_gemm_noshuffle_q4_k_q8_1_dp4a_ila_a8_bin` (llama/29056)
shaofeiqi
More... 11 days ago
vulkan: add Intel Xe flash attention optimization kernels (2/3, Xe-LPG Plus/Xe2/Xe3) (llama/24406)
Jiang, Fish
More... 12 days ago
metal : gate mul_mm_id src1 rescale behind ggml_prec (llama/29029)
Michael de Gans
More... 12 days ago
ggml : IQ1_M build prefix sums once per block (llama/28706)
Bartowski
More... 12 days ago
Performance tune for gemma4-26b-a4b flash attention shape. (llama/28450)
David M. Rogers
More... 12 days ago
opencl: add A8 Q4_0 non-MoE dp4a binary kernel (llama/29055)
shaofeiqi
More... 12 days ago
vad : reject n_encoder_layers other than 4 in model load (#4064)
Abir Deol
More... 12 days ago