ggml-org/llama.cpp

Pull Requests Commits
ci : improve release flow (#29913)
CISC committed 37 days ago
Verified f98b31c6
webgpu: add f16 support to fill/set_rows (#29897)
yomaytk committed 38 days ago
Verified 11fe0215
mtmd : fix deprecated strdup warning on Windows (#29863)
angt committed 38 days ago
Verified 836d5717
vendor : update cpp-httplib to 0.59.0 (#29886)
cabelo committed 38 days ago
Verified eec18f5d
server : fix laya abort by limiting n_batch to n_ubatch (#29903)
notforu777 committed 38 days ago
Verified 1537a0a8
common : add common_is_tty() helper and fix deprecated warnings on Windows (#29860)
angt committed 38 days ago
Verified edd6e2bb
chat : honor json_schema in Ling 3.0 parser (#29813)
devYRPauli committed 38 days ago
Verified 9bf55f4a
ci: fix flaky ADD_ADD f16 by using the fused ADD tolerance (#29904)
ServeurpersoCom committed 38 days ago
Verified a55e952b
graph: gather the recurrent states once so the reserve covers every split (#29856)
ServeurpersoCom committed 38 days ago
Verified 436f6f89
ggml-openvino: update to 2026.4.1, optimize performance, expand ops, improve device listing. (#29852)
ravi9 committed 38 days ago
Verified b92761a5
model : Add LFM2.5-Encoder-350M and LFM2.5-Encoder-230M (#29862)
tdakhran committed 38 days ago
Verified cb7934c5
qwen4exp : halve the indexer score memory (#29825)
ServeurpersoCom committed 38 days ago
Verified 889edf43
model: add support for clef decision model (text-only) (#29831)
ngxson committed 39 days ago
Verified 99b95488
CUDA: fuse shared experts into MMVQ (#29184)
am17an committed 39 days ago
Verified bed0a856
ci : use t4-medium for cuda jobs (#29842)
CISC committed 39 days ago
Verified 4ebdf2c7
spec : add probabilistic sampling for simple draft and MTP (#27694)
praneshgo committed 39 days ago
Verified 1fb7ef3e
ggml-cuda : fix cpy transposed path corrupting non-contiguous dst (#27663)
devYRPauli committed 39 days ago
Verified 134b2bb7
ggml-quants : avoid invalid rounding in qkx3 scale search (#29817)
devYRPauli committed 39 days ago
Verified 2923cf28
ggml-cpu : fix soft_max_back wrong output when dst aliases src1 (#27096)
devYRPauli committed 39 days ago
Verified dd4c286f
model: support nimble decision model (#29844)
ngxson committed 39 days ago
Verified 46ca246d
readme : add cmd install commands (#29850)
ggerganov committed 39 days ago
Verified d8fbd258
metal : add tensor API flash attention kernel for F16 KV (#29570)
ethanhq committed 39 days ago
Verified 926862e5
llama, server: add /v1/systemone API (models: laya, julia-1, lev, openjev, kev) (#29818)
ngxson committed 39 days ago
Verified a4cb4c61
common : remove fs_open_ifstream() by using u8path() (#29841)
angt committed 39 days ago
Verified 70849ee8
llama : silence unused-result warnings (#29839)
angt committed 39 days ago
Verified 8d81559f
llama : use GGML_ABORT instead of throw (#29840)
angt committed 39 days ago
Verified 6805ae35
opencl: use sigmoid f16 for bf16 (#29787)
lhez committed 39 days ago
Verified a8c9a4e7
SYCL: Q8_0 DMMV ESIMD and MMVQ wide load (#29186)
cwriter committed 39 days ago
Verified 392ded65
vulkan: disable large matmul tile on Samsung GPUs with 32KB shared memory (#28531)
jwsong98 committed 39 days ago
Verified 9e258a6e
sycl: large register file for D=512 FA vec kernels (#29062)
Titaniumtown committed 39 days ago
Verified b9332895
Terms Of Use Privacy Policy Refund Policy Impressum