ngxson/llama.cpp

Pull Requests Commits

server : (UI) fix copy to clipboard function

ngxson committed 362 days ago

6161e891

convert : fix RWKV v6 model conversion (#10913)

MollySophia committed 362 days ago

Verified 0a11f8b7

clip : disable GPU support (#10896)

ggerganov committed 363 days ago

Verified d408bb92

llama : minor grammar refactor (#10897)

ggerganov committed 363 days ago

Verified 5cab3e4a

tts : small QoL for easy model fetch (#10903)

ggerganov committed 363 days ago

Verified 36319dec

server : fix logprobs, make it OAI-compatible (#10783)

ngxson committed 363 days ago

Verified 57bb2c40

ggml: fix arm build with gcc (#10895)

angt committed 363 days ago

Verified a3c33b1d

llama : fix Roberta embeddings (#10856)

Ssukriti committed 363 days ago

Verified 2fffc52b

convert : Add support for Microsoft Phi-4 model (#10817)

fairydreaming committed 363 days ago

Verified 7585edbd

tests: disable GGUF test for bad value size (#10886)

JohannesGaessler committed 363 days ago

Verified cd920d0a

llama-run : improve progress bar (#10821)

ericcurtin committed 363 days ago

Verified 7909e858

ggml : fix arm build (#10890)

slaren committed 363 days ago

Verified 9177484f

tts : add OuteTTS support (#10784)

ggerganov committed 364 days ago

Verified 0bf2d10c

server: avoid overwriting Authorization header (#10878)

vesath committed 364 days ago

Verified 7bbb5acf

server : output embeddings for all tokens when pooling = none (#10861)

ggerganov committed 364 days ago

Verified 152610ed

server : add "tokens" output (#10853)

ggerganov committed 364 days ago

Verified 0e70ba68

server : (embeddings) using same format for "input" and "content" (#10872)

ngxson committed 364 days ago

Verified 46828872

docs: Fix HIP (née hipBLAS) in README (#10880)

brianredbeard committed 364 days ago

Verified 6b064c92

Revert "llama : add Falcon3 support (#10864)" (#10876)

slaren committed 364 days ago

Verified 4da69d1a

Use model->gguf_kv for loading the template instead of using the C API. (#10868)

dranger003 committed 364 days ago

Verified d62b532c

tests: add tests for GGUF (#10830)

JohannesGaessler committed 1 year ago

Verified 081b29bd

ggerganov committed 1 year ago

Verified 5437d4aa

cmake : fix "amd64" processor string (whisper/2638)

ggerganov committed 1 year ago

Verified 78f76676

vulkan : fix soft_max.comp division by zero (whisper/2633)

gn64 committed 1 year ago

Verified 8dd19a48

ggml : remove return from ggml_gallocr_allocate_node (ggml/1048)

danbev committed 1 year ago

Verified 130d0c90

ggml : add check for grad_accs (ggml/1046)

danbev committed 1 year ago

Verified 3919da8e

ggml : update ggml_backend_cpu_device_supports_op (#10867)

ggerganov committed 1 year ago

Verified 0006f5a7

server : fill usage info in embeddings and rerank responses (#10852)

krystiancha committed 1 year ago

Verified 05c3a444

llama : add Falcon3 support (#10864)

mokeddembillel committed 1 year ago

Verified 382bc7f2

readme : update typos (#10863)

ruanych committed 1 year ago

Verified 4f51968a

Older