ggml-org/llama.cpp

Pull Requests Commits

test ubuntu 26 for sanitizer

netrunnereve committed 12 minutes ago

Verified e211dcbf

Update ci-self-hosted-cpu.yml

netrunnereve committed 1 day ago

Verified 6f93f537

python 3.14 should work now

netrunnereve committed 1 day ago

12c1f38c

Merge https://github.com/ggerganov/llama.cpp into netrunnereve/ci

netrunnereve committed 1 day ago

75344008

requirements : fix numpy dependencies (#31508)

CISC committed 1 day ago

Verified 785322d1

sycl: Try PkgConfig for LevelZero includes / libs (#31076)

mctylr-gh committed 2 days ago

Verified dde879bc

opencl: add initial iq3 support (#31338)

shaofeiqi committed 2 days ago

Verified 060b2fea

hexagon : fix DMA transfers with strides > 24 bits (#31442)

marktodorovich committed 2 days ago

Verified a91eab67

mtmd : fix InternVL CLS token order (#30886)

boshjerns committed 2 days ago

Verified d5ef408e

tests : enable Gemma 4 in `test-llama-archs` (#31401)

nikwen committed 2 days ago

Verified 79bce0c8

llama : enable tensor split for LFM3 (#31431)

tdakhran committed 2 days ago

Verified bc428e40

vendor : update miniaudio to 0.11.26 (#31459)

cabelo committed 2 days ago

Verified f6312ad7

llama : fix rotation of attention tensors in layers with shared KV (#31406)

nikwen committed 2 days ago

Verified 0138937e

revert the server sanitize stuff

netrunnereve committed 2 days ago

Verified 790aeb99

fix dependencies

netrunnereve committed 2 days ago

471851c7

reshaping so mm on 2d instead of 3d tensor for lfm sc (#30831)

anthonymaltsev committed 2 days ago

Verified ddf48f85

try to run server sanitize on ubuntu 26

netrunnereve committed 2 days ago

876f9ff8

test nproc for server sanitize

netrunnereve committed 2 days ago

b594ce0f

if ubuntu 26 doesnt have compile errors in release mode we can just use a regular machine

netrunnereve committed 2 days ago

a68c0b36

server: cap shared decision prefixes at the first output (#30710)

aiqubits committed 2 days ago

Verified f3586e66

server : fix /v1/responses endpoint to accept extra_params (#30959)

Dgarc359 committed 2 days ago

Verified 2871678a

mtmd : resize Gemma 4 images without letterbox padding (#30922)

boshjerns committed 2 days ago

Verified 7bd18083

opencl: add fwht (#31434)

shaofeiqi committed 3 days ago

Verified 0ec4027a

chat : strip the think block in the qwen3-coder with reasoning_format none (#31380)

tdakhran committed 3 days ago

Verified 1052f7e1

sycl: fix f32 to q2_0/q4_0/q5_0 rounding in CPY (#31120)

Torchit1 committed 3 days ago

Verified 8956c769

see if we can use release mode for undefined on ubuntu 26

netrunnereve committed 3 days ago

Verified ae2d53c5

fix dependencies (https://github.com/ggml-org/llama.cpp/pull/31222)

netrunnereve committed 3 days ago

Verified 22068a17

ubuntu 26 has a working nproc

netrunnereve committed 3 days ago

d35ac494

netrunnereve committed 3 days ago

33776d4c

run self hosted cpu jobs on hf

netrunnereve committed 3 days ago

72f8189d

Older