ggerganov/llama.cpp

Pull Requests Commits

Merge branch 'master' into compilade/gguf-py-fix-old-numpy

compilade committed 315 days ago

aaf7bc89

flake.lock: Update (#8342)

ggerganov committed 315 days ago

Verified 7fdb6f73

labeler : updated sycl to match docs and code refactor (#8373)

Alcpz committed 315 days ago

Verified a130ecce

readme : fix web link error [no ci] (#8347)

b4b4o committed 315 days ago

Verified c4dd11d1

sycl : fix powf call in device code (#8368)

Alcpz committed 315 days ago

Verified 2ec846d5

scripts : fix sync for sycl

ggerganov committed 316 days ago

Verified 3f2d538b

ggerganov committed 316 days ago

2ee44c9a

tests : fix whitespace (#0)

ggerganov committed 316 days ago

6847d54c

feat: cuda implementation for `ggml_conv_transpose_1d` (ggml/854)

balisujohn committed 316 days ago

fde13b3b

common : preallocate sampling token data vector (#8363)

kevmo314 committed 316 days ago

Verified 470939d4

infill : assert prefix/suffix tokens + remove old space logic (#8351)

ggerganov committed 316 days ago

Verified 6f0dbf6a

common : avoid unnecessary logits fetch (#8358)

kevmo314 committed 316 days ago

Verified ffd00797

readme : add supported glm models (#8360)

youth123 committed 316 days ago

Verified 04ce3a8b

py : type-check all Python scripts with Pyright (#8341)

compilade committed 316 days ago

Verified 3fd62a6b

Update llama-cli documentation (#8315)

dspasyuk committed 316 days ago

Verified a8db2a9c

ci : add checks for cmake,make and ctest in ci/run.sh (#8200)

AlexsCode committed 316 days ago

Verified 4090ea55

readme : update bindings list (#8222)

andy-tai committed 316 days ago

Verified f1948f1e

gguf-hash: model wide and per tensor hashing using xxhash and sha1 (#8048)

mofosyne committed 316 days ago

Verified f7cab35e

llama : support glm3 and glm4 (#8031)

youth123 committed 316 days ago

Verified 905942ab

llama : fix n_rot default (#8348)

ggerganov committed 317 days ago

Verified b5040086

py : use cpu-only torch in requirements.txt (#8335)

compilade committed 317 days ago

Verified d39130a3

finetune: Rename command name in README.md (#8343)

standby24x7 committed 317 days ago

Verified b81ba1f9

finetune: Rename an old command name in finetune.sh (#8344)

standby24x7 committed 317 days ago

Verified 210eb9ed

server: Retrieve prompt template in /props (#8337)

bviksoe committed 317 days ago

Verified cb4d86c4

added support for Authorization Bearer tokens when downloading model (#8307)

dwoolworth committed 317 days ago

Verified 86e7299e

update main readme (#8333)

ngxson committed 317 days ago

Verified 60d83a01

llama : add early return for empty range (#8327)

danbev committed 318 days ago

Verified 87e25a1d

Detokenizer fixes (#8039)

jaime-m-p committed 318 days ago

Verified 213701b5

Reorganize documentation pages (#8325)

ngxson committed 318 days ago

Verified be20e7f4

llama : fix compile warning (#8304)

ggerganov committed 318 days ago

Verified 7ed03b89

Older