ngxson/llama.cpp

Pull Requests Commits

`tool-call`: fix Qwen 2.5 Coder support, add micro benchmarks, support trigger patterns for lazy grammars (#12034)

ochafik committed 291 days ago

Verified 669912d9

ci : fix xcframework artifact tag (#12191)

danbev committed 291 days ago

Verified fa31c438

ci : remove xframework upload (#12190)

danbev committed 291 days ago

Verified 3ccbfe5a

server : fix cache reuse logic (#12161)

Clauszy committed 291 days ago

Verified 06a92a19

llama : add xcframework build script (#11996)

danbev committed 291 days ago

Verified a057897a

ggml : portability fixes for VS 2017 (#12150)

mgroeber9110 committed 292 days ago

Verified 5bbe6a9f

readme : fix roadmap link (#12185)

ggerganov committed 292 days ago

Verified 20a9b8f5

main: allow preloading conversation with -p and add -st / --single-turn (#12145)

CISC committed 292 days ago

Verified 56d7a9f8

`server`: fix deadly typo in response_format.json_schema.schema handling (#12168)

ochafik committed 292 days ago

Verified 1a24c462

HIP: implement FlashAttention via rocWMMA for CDNA and RDNA3+ (#12032)

hjc4869 committed 292 days ago

Verified becade5d

ggerganov committed 293 days ago

dfd6b2c0

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

cmdr2 committed 293 days ago

b64d7cc2

ggerganov committed 293 days ago

3d1cf3cf

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

cmdr2 committed 293 days ago

0cbee131

ggerganov committed 293 days ago

8371d445

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

cmdr2 committed 293 days ago

87abb7e9

whisper : support GGML_BACKEND_DL (whisper/2843)

slaren committed 293 days ago

6d4c23b8

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

midnightmagic committed 293 days ago

6512a900

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

petterreinholdtsen committed 293 days ago

45120557

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

cmdr2 committed 293 days ago

f54a4ba1

scripts : sync-ggml-am.sh fix

ggerganov committed 293 days ago

aede2074

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

danbev committed 293 days ago

Verified 2679c3b5

tts: add speaker file support (#12048)

dm4 committed 293 days ago

Verified c43af927

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

slaren committed 293 days ago

Verified d5c63cd7

ggml : fix kleidiai build (#12159)

ag2s20150909 committed 293 days ago

Verified 9660ffef

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

ericcurtin committed 293 days ago

Verified c950a1f6

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

ngxson committed 293 days ago

Verified 7b69003a

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

qnixsynapse committed 293 days ago

Verified ece9745b

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

slaren committed 293 days ago

Verified cc473cac

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

CISC committed 294 days ago

Verified 14dec0c2

Newer Older