ochafik/llama.cpp

Pull Requests Commits

add llama_grammar_trigger_pattern

Olivier Chafik committed 1 year ago

ba7b185a

common_grammar_trigger: always use string value (+ optional token) instead of. variant

Olivier Chafik committed 1 year ago

e8272820

Merge remote-tracking branch 'origin/master' into tool-bench

Olivier Chafik committed 1 year ago

2e4f93c4

ggerganov committed 1 year ago

dfd6b2c0

cuda: unary ops as float + de-duplicate (ggml/1130)

cmdr2 committed 1 year ago

b64d7cc2

ggerganov committed 1 year ago

3d1cf3cf

cuda/vulkan: specify fp32-only support for some operations in supports_op (ggml/1129)

cmdr2 committed 1 year ago

0cbee131

ggerganov committed 1 year ago

8371d445

cuda/cpu: Increase support for fp16 unary operations (ggml/1125)

cmdr2 committed 1 year ago

87abb7e9

whisper : support GGML_BACKEND_DL (whisper/2843)

slaren committed 1 year ago

6d4c23b8

cmake : fix compile assumptions for power9/etc (whisper/2777)

midnightmagic committed 1 year ago

6512a900

Told cmake to install ggml-cpp.h as a public header file. (ggml/1126)

petterreinholdtsen committed 1 year ago

45120557

Support pure float16 add/sub/mul/div operations in the CUDA (and CPU) backend (ggml/1121)

cmdr2 committed 1 year ago

f54a4ba1

scripts : sync-ggml-am.sh fix

ggerganov committed 1 year ago

aede2074

ci : set GITHUB_ACTION env var for server tests (#12162)

danbev committed 1 year ago

Verified 2679c3b5

tts: add speaker file support (#12048)

dm4 committed 1 year ago

Verified c43af927

test-backend-ops : add option -p to filter by op params (#12155)

slaren committed 1 year ago

Verified d5c63cd7

ggml : fix kleidiai build (#12159)

ag2s20150909 committed 1 year ago

Verified 9660ffef

Adding UTF-8 support to llama.cpp (#12111)

ericcurtin committed 1 year ago

Verified c950a1f6

webui : add ?m=... and ?q=... params (#12148)

ngxson committed 1 year ago

Verified 7b69003a

SYCL: Move CPY kernels to a separate file and add few missing kernels (#12133)

qnixsynapse committed 1 year ago

Verified ece9745b

ggml-backend : keep paths in native string type when possible (#12144)

slaren committed 1 year ago

Verified cc473cac

main: use jinja chat template system prompt by default (#12118)

CISC committed 1 year ago

Verified 14dec0c2

main: update outdated system prompt message (followup to #12131) (#12132)

CISC committed 1 year ago

Verified 1782cdfe

common : add --system-prompt parameter, replace behavior of -p in conversation mode (#12131)

CISC committed 1 year ago

Verified 45a8e767

CUDA: compress mode option and default to size (#12029)

Green-Sky committed 1 year ago

Verified 80c41ddd

webui : minor typo fixes (#12116)

vynride committed 1 year ago

Verified 2cc4a5e4

convert : fix Norway problem when parsing YAML (#12114)

ngxson committed 1 year ago

Verified 06c2b156

ggml : upgrade init_tensor API to return a ggml_status (#11854)

WilliamTambellini committed 1 year ago

Verified 70680c48

llama : add Phi-4-mini support (supersede #12099) (#12108)

ngxson committed 1 year ago

Verified c43a3e79

Older