ggml-org/llama.cpp

Pull Requests Commits

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

ggerganov committed 59 days ago

Verified 5266f24d

sync : ggml (#28379)

ggerganov committed 59 days ago

Verified 64a155d2

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

ngxson committed 60 days ago

Verified 163a4079

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

nikwen committed 60 days ago

Verified 8f83678f

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

danbev committed 60 days ago

Verified 86b351fd

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

eapache committed 60 days ago

Verified d509cb1e

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

angt committed 60 days ago

Verified 4cbe8b07

ggml : remove GGML_CUDA_PEER_MAX_BATCH_SIZE (#28177)

angt committed 60 days ago

Verified 24f5bf8a

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

ggerganov committed 60 days ago

Verified a529af96

vendor: update BoringSSL to 0.20260903.0 (#28354)

cabelo committed 60 days ago

Verified 38521ec3

ci : disable failing openvino tests (#28347)

ravi9 committed 60 days ago

Verified 0ef4d560

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

angt committed 60 days ago

Verified c390d0ab

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

taronaeo committed 60 days ago

Verified 832fd6f1

src : add n_expert_used_max function (#28323)

danbev committed 60 days ago

Verified 9a4843cf

sycl: fuse rms_norm+mul+add and add+add residual chains (#27610)

newjordan committed 60 days ago

Verified 6703d789

SYCL: Refactor GGML_SYCL_ENABLE_MKL_FA to global var (#26863)

johnkarlhill committed 60 days ago

Verified f9f09f02

llama: fix whole source code rebuilt on each new commit (#28278)

ngxson committed 60 days ago

Verified d230ddd7

common/json-schema : fix GBNF grammar generation for empty object schemas (#28279)

SergeySklyarov committed 60 days ago

Verified c5a5535e

opencl: quant lm_head / decode GEMV and medium-batch GEMM optimizations (speculative decoding/MTP) (#26477)

wanghqc committed 60 days ago

Verified 95ef7fc1

tune MMVQ to MMQ crossover for SM87 (#28285)

kbenkhaled committed 60 days ago

Verified 8c1a2516

snapdragon: ci updates to use new run script (#28293)

max-krasnyansky committed 60 days ago

Verified d30500b8

ops: add Hexagon to ops.md and update main README.md (#28263)

tboinovski1 committed 60 days ago

Verified e107984b

server : use pytest-xdist for server tests (#28298)

danbev committed 60 days ago

Verified 42f0225f

mtmd: propagate const to preproc class (#28310)

ngxson committed 60 days ago

Verified de8656bd

metal : add sparse FA (#28098)

ggerganov committed 60 days ago

Verified 7bb0fc18

metal : fix glu dispatch with ne00 = 1 (#28306)

ggerganov committed 61 days ago

Verified 0df017d6

mtmd : add `const` in various places (#28307)

madsmtm committed 61 days ago

Verified f45576aa

CUDA: Allow concurrent streams per split for multi-GPU (#28198)

tannerbruhn committed 61 days ago

Verified 0ba6499c

vulkan: fix FA dequant path engagement (#28190)

Nathanw1014 committed 61 days ago

Verified c7bda030

sycl : enhance the api to support peer-to-peer copy (#27550)

arthw committed 61 days ago

Verified 0df974d7

Newer Older