ochafik/llama.cpp

Pull Requests Commits

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

ochafik committed 313 days ago

40951c81

ci : enable winget package updates (#13734)

slaren committed 314 days ago

Verified b775345d

ci : add winget package updater (#13732)

slaren committed 314 days ago

Verified a70a8a69

hparams : initialize arrays (#13728)

ggerganov committed 314 days ago

Verified d13d0f61

llama : allow custom list of swa_layers (#13726)

ngxson committed 314 days ago

Verified 8a2afb75

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

ochafik committed 314 days ago

f0d5df28

server : support audio input (#13714)

ngxson committed 314 days ago

Verified 9ecf3e66

CANN: Support MUL_MAT_ID for q8_0 and q4_0 (#13705)

noemotiovon committed 314 days ago

Verified faaaff5f

ggml : fix the order of ggml_unary_op (#13718)

ngxson committed 314 days ago

Verified e16c4731

vulkan: support CPY from any type to itself (#13695)

jeffbolznv committed 314 days ago

Verified 1dcd0196

vulkan: Disable coopmat/coopmat2/bfloat extensions if glslc doesn't support it (#13696)

jeffbolznv committed 314 days ago

Verified c10ed6cb

use LOG_WARN to replace `std::cerr` (#13657)

foldl committed 314 days ago

Verified a127ff17

release : fix windows hip release (#13707)

slaren committed 314 days ago

Verified 3079e9ac

tts : fix n_ubatch + make WavTokenizer cache-less (#13713)

ggerganov committed 315 days ago

Verified 8a1d206f

mtmd : add ultravox audio input (#13623)

ngxson committed 315 days ago

Verified 797990c4

common: Include torch package for s390x (#13699)

taronaeo committed 315 days ago

Verified ab863357

server : pad small embedding batches (#13692)

ggerganov committed 315 days ago

Verified cc74d5be

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

CISC committed 315 days ago

Verified 5be24af7

sycl : Remove waits from function calls (#13702)

s-Nick committed 315 days ago

Verified d394a9ae

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

Ewan Crawford committed 315 days ago

Verified 6b56a646

opencl: Add support for multiple devices (#12622)

Henry Linjamäki committed 315 days ago

Verified a4e8912d

opencl: fix couple crashes (#12795)

Henry Linjamäki committed 316 days ago

Verified edbf42ed

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

slaren committed 316 days ago

Verified d643bb2c

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

ggerganov committed 316 days ago

Verified 8e186ef0

server : improve error reporting (#13680)

ggerganov committed 316 days ago

Verified 5fbfe384

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

antichristHater committed 316 days ago

Verified c76532e7

examples : switch retrieval to llama_encode (#13685)

CISC committed 316 days ago

Verified 2aa777d8

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

emmanuel-ferdman committed 316 days ago

Verified eb0f5c28

ggml : add ggml_gelu_erf() (#13667)

ngxson committed 316 days ago

Verified cf4cb59e

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

R-Dson committed 316 days ago

Verified 0d5c7421

Older