Skip to content

Actions: ggml-org/llama.cpp

Actions

Publish Docker image

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
docker.yml
688 workflow runs
688 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

sycl : update support conditions (#9394) Publish Docker image #14464: Commit 51b6038 pushed by NeoZhangJianyu
46m 35s master
master
46m 35s
arg : bring back missing ifdef (#9411) Publish Docker image #14463: Commit 6cd4e03 pushed by ngxson
1h 18m 53s master
master
1h 18m 53s
enable --special arg for llama-server (#9419) Publish Docker image #14462: Commit 8d300bd pushed by ngxson
32m 9s master
master
32m 9s
llama : move random seed generation to the samplers (#9398) Publish Docker image #14461: Commit 49006c6 pushed by slaren
49m 8s master
master
49m 8s
metal : fix compile warning with GGML_METAL_NDEBUG (#0) Publish Docker image #14460: Commit 00ba2ff pushed by ggerganov
53m 40s master
master
53m 40s
RWKV v6: Add time_mix_decay_w1/w2 in quant exclusion list (#9387) Publish Docker image #14459: Commit 0b4ac75 pushed by ggerganov
30m 39s master
master
30m 39s
make : do not run llama-gen-docs when building (#9399) Publish Docker image #14458: Commit fb3f249 pushed by ggerganov
32m 51s master
master
32m 51s
common : move arg parser code to arg.cpp (#9388) Publish Docker image #14457: Commit bfe76d4 pushed by ngxson
33m 34s master
master
33m 34s
rpc : fix segfault with nkvo (#9389) Publish Docker image #14456: Commit 293bebe pushed by rgerganov
1h 32m 17s master
master
1h 32m 17s
ggml : vector length agnostic SVE support (#9290) Publish Docker image #14455: Commit 5fac4d5 pushed by ggerganov
1h 13m 32s master
master
1h 13m 32s
llama : minor sampling refactor (2) (#9386) Publish Docker image #14454: Commit 5fb5e24 pushed by slaren
51m 24s master
master
51m 24s
CUDA: fix variable name conflict for Windows build (#9382) Publish Docker image #14453: Commit 8e6e2fb pushed by JohannesGaessler
32m 21s master
master
32m 21s
Overlap cmdbuffer creation and cmdbuffer execution in Vulkan backend … Publish Docker image #14452: Commit daa9623 pushed by 0cc4m
31m 20s master
master
31m 20s
cuda : fix FA Q src index (1 -> 0) (#9374) Publish Docker image #14451: Commit e079bff pushed by ggerganov
38m 21s master
master
38m 21s
common : bring back missing args, add env var duplication check (#9375) Publish Docker image #14450: Commit 3f7ccfd pushed by ngxson
32m 32s master
master
32m 32s
common : restore --n-gpu-layers (#9371) Publish Docker image #14449: Commit a249843 pushed by ngxson
47m 45s master
master
47m 45s
llama : refactor samplers internal implementation (#9370) Publish Docker image #14448: Commit 19f4a7b pushed by slaren
37m 41s master
master
37m 41s
[SYCL] add check malloc result on device (#9346) Publish Docker image #14447: Commit 2a358fb pushed by airMeng
51m 5s master
master
51m 5s
llama : sanitize tokens in the upper bound (#9359) Publish Docker image #14446: Commit eae5971 pushed by slaren
51m 17s master
master
51m 17s
imatrix : fix arg parser for imatrix (#9366) Publish Docker image #14445: Commit 00b02bb pushed by ngxson
46m 11s master
master
46m 11s
metal : update support condition for im2col + fix warning (#0) Publish Docker image #14444: Commit a876861 pushed by ggerganov
31m 24s master
master
31m 24s
llama : set attrs of mislabelled EOT/EOM tokens (#9348) Publish Docker image #14443: Commit fbb7fcf pushed by ggerganov
30m 19s master
master
30m 19s
llama.android : fix build (#9350) Publish Docker image #14442: Commit a5b5d9a pushed by ggerganov
1h 40m 13s master
master
1h 40m 13s
llama : fix empty ring buffer push (#9358) Publish Docker image #14441: Commit f12295b pushed by ggerganov
1h 10m 3s master
master
1h 10m 3s
llama : sanitize invalid tokens (#9357) Publish Docker image #14440: Commit faf69d4 pushed by ggerganov
30m 14s master
master
30m 14s
ProTip! You can narrow down the results and go further in time using created:<2024-09-07 or the other filters available.