ggerganov/llama.cpp

Pull Requests Commits
jinja : implement call statement (#24847)
CISC committed 133 days ago
Verified bf533823
mtmd: add load progress callback (#24865)
ngxson committed 133 days ago
Verified 2f89acc2
server: add "verbose" field to schema (#24864)
ngxson committed 133 days ago
Verified bfa32191
server: real-time model load progress tracking via /models/sse (#24828)
ngxson committed 133 days ago
Verified d6d89958
minor : clean-up whitespaces (#24862)
ggerganov committed 133 days ago
Verified 8a118ee8
spec : Support Step3.5/3.7 flash mtp3 (#24340)
forforever73 committed 133 days ago
Verified d7895274
common/peg : refactor until gbnf grammar generation (#24839)
aldehir committed 133 days ago
Verified 063d9c15
common/json-schema-to-grammar : align spacing rules with parsers (#24835)
aldehir committed 134 days ago
Verified c5760701
fix(hexagon): use padded stride for ssm-conv weights (#24470)
BiReRa committed 134 days ago
Verified 4a809431
llama : use LLM_KV for quantization_version & file_type (#24802)
angt committed 134 days ago
Verified 84de01a1
arg: try fixing test-args-parser randomly fails (#24826)
ngxson committed 134 days ago
Verified 75f460ac
release: add missing link for win opencl adreno arm64 (#24809)
muhammad-salem committed 134 days ago
Verified 84528246
server: avoid forwarding auth headers in CORS proxy (#24373)
ItsMatti4 committed 134 days ago
Verified e27f3085
docker : prebuild web UI for s390x build [no release] (#24829)
aldehir committed 134 days ago
Verified 67e9fd3b
model : glm-dsa load DSA indexer tensors as optional (#24770)
davidrhodus committed 134 days ago
Verified 796f41be
ggml : optimize AMX (#24806)
angt committed 134 days ago
Verified 37a77fb0
convert : more consistent handling of rope_parameters (#24833)
CISC committed 134 days ago
Verified f4043fec
ggml-webgpu: add adapter toggles for F16 on Vulkan + NVIDIA
yomaytk committed 135 days ago
Verified f449e055
server: refactor child --> router communication (#24821)
ngxson committed 135 days ago
Verified 2b686a91
server : optimize get_token_probabilities (#24796)
angt committed 135 days ago
Verified 4b48a53b
mtmd, arg: fix utf8 handling on windows (#24779)
ngxson committed 135 days ago
Verified e475fa2b
server: remove all internal mentions about "webui" (#24817)
ngxson committed 135 days ago
Verified 175147e8
arg: Add comment line support to --api-key-file (#23168)
kucharskim committed 135 days ago
Verified fabde3bf
vendor : update cpp-httplib to 0.48.0 (#24787)
cabelo committed 135 days ago
Verified 0d2d9ccb
server: add --agent arg, remove redundant webui naming compat (#24801)
ngxson committed 135 days ago
Verified 8c2d6f64
docker : build the UI (#24794)
aldehir committed 135 days ago
Verified 38724ab5
mtmd: several bug fixes (#24784)
ngxson committed 135 days ago
Verified e2e7a9b2
spec: support eagle3 for qwen3.5 & 3.6 (#24593)
ruixiang63 committed 135 days ago
Verified b14e3fb9
server: fix non-bound n_discard value (ctx shifting) (#24786)
ngxson committed 135 days ago
Verified 159d093a
sync : ggml
ggerganov committed 135 days ago
5fd2dc2c
Terms Of Use Privacy Policy Refund Policy Impressum