ochafik/llama.cpp

Pull Requests Commits

ochafik committed 1 year ago

32826e18

llama : skip loading unused tensors (#12004)

ggerganov committed 1 year ago

Verified 51f311e0

doc: update contributing guidelines [no ci] (#11969)

JohannesGaessler committed 1 year ago

Verified 586d5fe6

CUDA: correct the lowest Maxwell supported by CUDA 12 (#11984)

PureJourney committed 1 year ago

Verified ecc8e3ae

MUSA: support ARM64 and enable dp4a .etc (#11843)

BodhiHu committed 1 year ago

Verified 0b3863ff

clip : fix visual encoders with no CLS (#11982)

alex-jw-brooks committed 1 year ago

Verified ee02ad02

server (webui): Fix Premature Submission During IME Conversion (#11971)

mmngays committed 1 year ago

Verified c392e509

ggml-cpu: Add CPU backend support for KleidiAI library (#11390)

chaxu01 committed 1 year ago

Verified c5d91a74

ggml: aarch64: implement SVE kernels for q3_K_q8_K vector dot (#11917)

Vithulep committed 1 year ago

Verified 4806498b

run : add --chat-template-file (#11961)

engelmi committed 1 year ago

Verified 0d559580

doc: add links to ggml examples [no ci] (#11958)

JohannesGaessler committed 1 year ago

Verified d04e7163

common : add llama.vim preset for Qwen2.5 Coder (#11945)

danbev committed 1 year ago

Verified d07c6213

speculative : update default params (#11954)

ggerganov committed 1 year ago

Verified abd4d0bc

llama : fix indentation in llama-grammar [no ci] (#11943)

danbev committed 1 year ago

Verified 9626d935

server : (webui) Enable communication with parent html (if webui is in iframe) (#11940)

igardev committed 1 year ago

Verified b58934c1

tool-call: refactor common chat / tool-call api (+ tests / fixes) (#11900)

ochafik committed 1 year ago

Verified 63e489c0

server : add TEI API format for /rerank endpoint (#11942)

ngxson committed 1 year ago

Verified 63ac1285

scripts: corrected encoding when getting chat template (#11866) (#11907)

MoonRide303 committed 1 year ago

Verified 5137da7b

docs : Fix duplicated file extension in test command (#11935)

xiaobing318 committed 1 year ago

Verified 09aaf4f1

CUDA: use async data loading for FlashAttention (#11894)

JohannesGaessler committed 1 year ago

Verified 73e2ed3c

update release requirements (#11897)

netrunnereve committed 1 year ago

Verified f7b1116a

server : fix divide-by-zero in metrics reporting (#11915)

aviallon committed 1 year ago

Verified c4d29baf

vulkan: implement several ops relevant for ggml_opt (#11769)

remyoudompheng committed 1 year ago

Verified 2eea03d8

server : bump httplib to 0.19.0 (#11908)

ngxson committed 1 year ago

Verified 0f2bbe65

common : Fix a typo in help (#11899)

standby24x7 committed 1 year ago

Verified fe163d5b

ci : fix (again) arm64 build fails (#11895)

ngxson committed 1 year ago

Verified 818a340e

vulkan: support multi/vision rope, and noncontiguous rope (#11902)

jeffbolznv committed 1 year ago

Verified bf42a23d

metal : fix the crash caused by the lack of residency set support on Intel Macs. (#11904)

halechan committed 1 year ago

Verified c2ea16f2

scripts: fix compare-llama-bench commit hash logic (#11891)

JohannesGaessler committed 1 year ago

Verified 6dde1782

examples: fix typo in imatrix/README.md (#11884)

708-145 committed 1 year ago

Verified fc10c38d

Older