ggerganov/llama.cpp

Pull Requests Commits

cmake : add GGML_BUILD and GGML_SHARED macro definitions (#8281)

akemimadoka committed 363 days ago

Verified 1d894a79

Enabled more data types for oneMKL gemm_batch (#8236)

OuadiElfarouki committed 363 days ago

Verified 1f3e1b66

convert : remove AWQ remnants (#8320)

ggerganov committed 364 days ago

Verified 148ec970

llama : minor indentation during tensor loading (#8304)

ggerganov committed 364 days ago

Verified 2cccbaa0

CUDA: MMQ support for iq4_nl, iq4_xs (#8278)

JohannesGaessler committed 364 days ago

Verified 8e558309

CUDA: revert part of the RDNA1 optimizations (#8309)

daniandtheweb committed 364 days ago

Verified 0a423800

llama : streamline embeddings from "non-embedding" models (#8087)

iamlemec committed 364 days ago

Verified d12f7810

CUDA: fix MMQ stream-k rounding if ne00 % 128 != 0 (#8311)

JohannesGaessler committed 364 days ago

Verified bcefa03b

readme : fix minor typos [no ci] (#8314)

pouwerkerk committed 364 days ago

Verified 5a7447c5

passkey : add short intro to README.md [no-ci] (#8317)

danbev committed 364 days ago

Verified 61ecafa3

llama : prefer n_ over num_ prefix (#8308)

ggerganov committed 364 days ago

Verified aa5898dc

contributing : update guidelines (#8316)

ggerganov committed 364 days ago

Verified 6c05752c

[SYCL] Fix WARP_SIZE=16 bug of Intel GPU (#8266)

luoyu-intel committed 364 days ago

Verified a9554e20

py : switch to snake_case (#8305)

ggerganov committed 364 days ago

Verified e235b267

rm get_work_group_size() by local cache for performance (#8286)

NeoZhangJianyu committed 364 days ago

Verified f09b7cb6

cli: add EOT when user hit Ctrl+C (#8296)

ngxson committed 364 days ago

Verified a38b884c

llama : add OpenELM support (#7359)

icecream95 committed 364 days ago

Verified d7fd29ff

tokenize : add --show-count (token) option (#8299)

danbev committed 364 days ago

Verified 6f63d646

build: Export hf-to-gguf as snakecase

ditsuke committed 364 days ago

51d2ebad

doc: Add context for why we add an explicit pytorch source

ditsuke committed 364 days ago

1e920018

chore: Remove rebase artifacts

ditsuke committed 364 days ago

01a5f065

chore: Fixup requirements and build

ditsuke committed 364 days ago

07786a61

chore: ignore all __pychache__

ditsuke committed 364 days ago

de14e2ea

fix: Update script paths in CI scripts

ditsuke committed 364 days ago

82192291

fix: Actually include scripts in build

ditsuke committed 364 days ago

b1c3f26e

build(python): Package scripts with pip-0517 compliance

ditsuke committed 364 days ago

b0a46993

Inference support for T5 and FLAN-T5 model families (#5763)

fairydreaming committed 364 days ago

Verified 807b0c49

tests : add _CRT_SECURE_NO_WARNINGS for WIN32 (#8231)

danbev committed 1 year ago

Verified f8c4c073

llama : suppress unref var in Windows MSVC (#8150)

danbev committed 1 year ago

Verified 402d6fef

convert : fix gemma v1 tokenizer convert (#8248)

ggerganov committed 1 year ago

Verified 20fc3804

Newer Older