ggml-org/llama.cpp

Pull Requests Commits

MA_MAX_FILTER_ORDER

ngxson committed 2 minutes ago

7c609da0

ngxson committed 2 minutes ago

3fae7deb

ngxson committed 1 hour ago

9168b27c

Merge branch 'master' into xsn/mtmd_helper_resampler

ngxson committed 1 hour ago

22556eda

mtmd: add mtmd_helper_resampler

ngxson committed 1 hour ago

58ebdc69

ggml-zdnn: accept non-zdnn tensors, invalidate compute tensors after every op (#31824)

taronaeo committed 6 hours ago

Verified a4d4f2fd

server : fix response_format json_schema when schema is not nested in the json_schema wrapper (#28697)

linsen458-spec committed 7 hours ago

Verified 1945793e

ggml : implement the backward pass for TRI (#30712)

losewayy committed 7 hours ago

Verified 0eebb6ed

tests : keep dummy ffn.act scales away from zero (#31940)

ggerganov committed 7 hours ago

Verified d628a98f

mtp: read the target hidden states from a device buffer (#31927)

am17an committed 7 hours ago

Verified a8fad21e

ui: fold, preview and rearrange the sidebar's sections (#31936)

allozaur committed 7 hours ago

Verified b39680c4

ggml-backend: don't upload inputs that are not read (#31419)

ArshM17-NV committed 7 hours ago

Verified 806b3c2b

models : Attach Granite NVFP4 weight scales (#31449)

jjperry69 committed 8 hours ago

Verified 0c6dca2f

ci : Run gfx1151 ROCm job on Strix Halo Devlab runners (#31567)

iswaryaalex committed 8 hours ago

Verified fc0be861

metal : prevent out-of-bounds writes to the Metal FA output buffer (#31662)

realMoana committed 8 hours ago

Verified e01c9f18

metal : make ggml_tri select instead of scaling by the comparison (#30711)

losewayy committed 8 hours ago

Verified 4b46d965

opencl : include climits (#31935)

CISC committed 9 hours ago

Verified f3178366

mtmd: Pocket TTS - add generic support for temperature set via API (#31655)

rjtokenring committed 9 hours ago

Verified 2d99adb1

RPC: Improve loading times (#29413)

am17an committed 10 hours ago

Verified cf92c132

ggml : support YaRN truncation config on openvino, sycl, vulkan, webgpu, rpc (#30802)

tokinasin committed 10 hours ago

Verified 9f0d80cf

sycl: cache device-id (#31126)

Titaniumtown committed 11 hours ago

Verified a0ad695c

tests: bound the test_rope tolerance by the f32 angle resolution (#31874)

ServeurpersoCom committed 11 hours ago

Verified 6590d25a

opencl: add f32 MUL_MAT_ID (#31783)

lhez committed 12 hours ago

Verified 53eb6694

ggml-zdnn: fix release binary not detecting backend lib (#31905)

taronaeo committed 12 hours ago

Verified d78f4255

mtmd: refactoring: remove clip.h, consolidate code into mtmd (#31865)

ngxson committed 1 day ago

Verified 7d7f0287

cpu: enable SpacemiT IME2 MXFP4 dense repack (#31776)

gitGurugu committed 1 day ago

Verified b65bf692

llamafile: impl bf16 and q8_0 vxe (#31866)

taronaeo committed 1 day ago

Verified a3c7cf08

ggml : update CUDA/Metal radix Top-K to make tied selections deterministic (#31084)

sanmai committed 1 day ago

Verified 57d04820

ggml-cuda : add d_state=64 fast path to SSM_SCAN kernel (#31818)

sargentmajord committed 1 day ago

Verified 99820049

moe-cache : ensure CPU part does not wait for the cached experts (#31888)

sanmai committed 1 day ago

Verified cf34d311

Older