ggerganov/llama.cpp

Pull Requests Commits

ui : shared model display primitives

allozaur committed 4 hours ago

410052bf

ui : optional sanitized raw HTML in markdown

allozaur committed 4 hours ago

fc0cb79b

ui : model download pipeline

allozaur committed 4 hours ago

ba274f7c

ui : model memory-fit estimation

allozaur committed 4 hours ago

0054a622

ui : Hugging Face Hub data layer

allozaur committed 4 hours ago

6aa3a00d

ui : model id grammar for sidecars, quants and capability parsing

allozaur committed 4 hours ago

51227a12

ui : type-safe API types, fetch helpers and download-ready models store plumbing

allozaur committed 4 hours ago

a6c9bc97

server : fix deadlock when removing a finished download

allozaur committed 6 hours ago

e6f1d61c

common : resolve <quant>-<sidecar> download tags and list cached sidecars

allozaur committed 6 hours ago

ff33779b

metal : add remaining fa-vec tunings for M3 (#28396)

init-22 committed 10 hours ago

Verified 427291b5

ui : fix MCP image attachments not displayed in tool block (#25789) (#28089)

nachobh committed 11 hours ago

Verified 85d5703a

opencl: extend the elementwise and data‐movement op coverage (#27633)

wanghqc committed 12 hours ago

Verified 1548a240

opencl: add Adreno xmem SDPA path (#26331)

happyyzy committed 12 hours ago

Verified 4acf4a4c

ci : move more jobs to ccache-buckets (#28375)

CISC committed 15 hours ago

Verified 8b4b3558

ui: export conversations from database instead of cached store (#27432)

intel00000 committed 16 hours ago

Verified 1863ac03

model : add Tencent Hy 4 (hy_v4) preview architecture support (#28127)

Little0o0 committed 16 hours ago

Verified 49c0dc82

llama.cpp : bump version to 0.4.0 (#28386)

ggerganov committed 17 hours ago

Verified 5266f24d

sync : ggml (#28379)

ggerganov committed 17 hours ago

Verified 64a155d2

model, mtmd: fix gemma4 vision handling (#28335)

ngxson committed 19 hours ago

Verified 163a4079

metal : add remaining fa-vec tunings for M3 Max (#28373)

nikwen committed 19 hours ago

Verified 8f83678f

ggml : replace compile definitions with version.h.in (#28364)

danbev committed 20 hours ago

Verified 86b351fd

Don't use npx inside a package.json script (#28270)

eapache committed 21 hours ago

Verified d509cb1e

ggml : don't crash when backend search path can't be read (#28271)

angt committed 22 hours ago

Verified 4cbe8b07

ggml : remove GGML_CUDA_PEER_MAX_BATCH_SIZE (#28177)

angt committed 22 hours ago

Verified 24f5bf8a

docs : update maintainer PRs link and regenerate AUTHORS (#28365)

ggerganov committed 22 hours ago

Verified a529af96

vendor: update BoringSSL to 0.20260903.0 (#28354)

cabelo committed 22 hours ago

Verified 38521ec3

ci : disable failing openvino tests (#28347)

ravi9 committed 23 hours ago

Verified 0ef4d560

common : make build info output stream configurable (#28322)

angt committed 23 hours ago

Verified c390d0ab

ggml-cpu(s390x) : fix q5_1 uninitialized v_acc (#28332)

taronaeo committed 23 hours ago

Verified 832fd6f1

src : add n_expert_used_max function (#28323)

danbev committed 1 day ago

Verified 9a4843cf

Older