ngxson/llama.cpp

Pull Requests Commits

add audio support on webui

ngxson committed 1 year ago

0d36c6b2

server : support audio input

ngxson committed 1 year ago

e55a682b

mtmd : add ultravox audio input (#13623)

ngxson committed 1 year ago

Verified 797990c4

common: Include torch package for s390x (#13699)

taronaeo committed 1 year ago

Verified ab863357

server : pad small embedding batches (#13692)

ggerganov committed 1 year ago

Verified cc74d5be

gguf-py : correct charsmap parameter typing (#13701)

CISC committed 1 year ago

Verified 5be24af7

sycl : Remove waits from function calls (#13702)

s-Nick committed 1 year ago

Verified d394a9ae

SYCL: Avoid using with SYCL-Graph for unsupported nodes (#13587)

Ewan Crawford committed 1 year ago

Verified 6b56a646

opencl: Add support for multiple devices (#12622)

Henry Linjamäki committed 1 year ago

Verified a4e8912d

opencl: fix couple crashes (#12795)

Henry Linjamäki committed 1 year ago

Verified edbf42ed

releases : build CPU backend separately (windows) (#13642)

slaren committed 1 year ago

Verified d643bb2c

hparams : support models for which all layers use SWA (#13682)

ggerganov committed 1 year ago

Verified 8e186ef0

server : improve error reporting (#13680)

ggerganov committed 1 year ago

Verified 5fbfe384

convert : add qwen2vl support for unsloth merges (#13686)

antichristHater committed 1 year ago

Verified c76532e7

examples : switch retrieval to llama_encode (#13685)

CISC committed 1 year ago

Verified 2aa777d8

gguf-py : display the invalid gguf type (#13687)

emmanuel-ferdman committed 1 year ago

Verified eb0f5c28

ggml : add ggml_gelu_erf() (#13667)

ngxson committed 1 year ago

Verified cf4cb59e

server : Add the endpoints /api/tags and /api/chat (#13659)

R-Dson committed 1 year ago

Verified 0d5c7421

server : fix first message identification (#13634)

doringeman committed 1 year ago

Verified 42158ae2

kv-cache : simplify the interface (#13660)

ggerganov committed 1 year ago

Verified 797f2ac0

model : disable SWA for Phi models (#13676)

ggerganov committed 1 year ago

Verified b44890df

musa: Upgrade MUSA SDK version to rc4.0.1 and use mudnn::Unary::IDENTITY op to accelerate D2D memory copy (#13647)

yeahdongcn committed 1 year ago

Verified 33983057

vulkan: fix warnings (#13626)

netrunnereve committed 1 year ago

Verified fb1cab20

mtmd-helper : bug fix to token batching in mtmd (#13650)

l3utterfly committed 1 year ago

Verified b7a17463

model : fix llama4 graph (#13663)

ggerganov committed 1 year ago

Verified be023969

llama : remove llama_kv_cache_view API + remove deprecated (#13653)

ggerganov committed 1 year ago

Verified a4090d11

CUDA: skip fully masked-out KV in FA vec kernel (#13584)

JohannesGaessler committed 1 year ago

Verified b69f1647

tests : avoid github urls due to throttling (#13654)

CISC committed 1 year ago

Verified 759e37b0

sycl: disable reorder for sycl mulmat (#13536)

sgeor255 committed 1 year ago

Verified 4245e622

Set GLM4 blk.*.attn_output.weight, kqv_out-* matmul to GGML_PREC_F32 to fix infinity values in output (#13639)

0cc4m committed 1 year ago

Verified c9c64dee

Older