Skip to content

Actions: ggml-org/llama.cpp

Actions

Server

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
server.yml
15,097 workflow runs
15,097 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

Add Gemma3n multimodal support with MobileNetV5 vision encoder Server #24761: Pull request #18256 synchronize by esemsc-ss2524
Action required simrnsingh:feat-gemma3n-vision
simrnsingh:feat-gemma3n-vision
Action required
cmake: Added more x86_64 CPU backends when building with GGML_CPU_ALL_VARIANTS=On Server #24760: Pull request #18186 synchronize by bberberov
In progress bberberov:more-cpu-backends
bberberov:more-cpu-backends
In progress
ggml-cuda: use CMAKE_CUDA_ARCHITECTURES if set when GGML_NATIVE=ON Server #24759: Pull request #18413 opened by QDelta
14m 9s QDelta:master
QDelta:master
14m 9s
full modern bert support Server #24758: Pull request #18330 synchronize by ryan-mangeno
17m 42s ryan-mangeno:full-modern-bert-support
ryan-mangeno:full-modern-bert-support
17m 42s
common: fix return value check for setpriority Server #24757: Pull request #18412 synchronize by o7si
12m 41s o7si:setpriority
o7si:setpriority
12m 41s
common: fix return value check for setpriority Server #24756: Pull request #18412 opened by o7si
9m 29s o7si:setpriority
o7si:setpriority
9m 29s
[model] Add support for Plamo3 Server #24755: Pull request #17304 synchronize by mmnga
12m 28s mmnga:features/suppert-plamo-3
mmnga:features/suppert-plamo-3
12m 28s
Gigachat 3 tool parser and tests Server #24754: Pull request #17924 synchronize by Mishusha
Action required Mishusha:feature/gigachat_v3_tool_parser
Mishusha:feature/gigachat_v3_tool_parser
Action required
[model] Add support for Plamo3 Server #24753: Pull request #17304 synchronize by mmnga
13m 1s mmnga:features/suppert-plamo-3
mmnga:features/suppert-plamo-3
13m 1s
[model] Add support for Plamo3 Server #24752: Pull request #17304 synchronize by mmnga
42m 14s mmnga:features/suppert-plamo-3
mmnga:features/suppert-plamo-3
42m 14s
rpc: fix segfault on invalid endpoint format Server #24751: Pull request #18387 synchronize by o7si
45m 7s o7si:issue-18377
o7si:issue-18377
45m 7s
ggml-cuda: Use same regex for GGML_NATIVE=OFF (#18407) Server #24750: Commit 06705fd pushed by am17an
34m 4s master
master
34m 4s
llama: fix magic number of 999 for GPU layers Server #24749: Pull request #18266 synchronize by JohannesGaessler
52m 54s JohannesGaessler:llama-fp-ngl-magic-number
JohannesGaessler:llama-fp-ngl-magic-number
52m 54s
llama-fit-params: fix overflow check Server #24748: Pull request #18354 synchronize by JohannesGaessler
25m 57s JohannesGaessler:llama-fp-fix-overflow
JohannesGaessler:llama-fp-fix-overflow
25m 57s
ggml-cuda: Use same regex for GGML_NATIVE=OFF Server #24747: Pull request #18407 opened by am17an
13m 0s am17an:cuda-same-regex
am17an:cuda-same-regex
13m 0s
mtmd: clarify that we no longer accept AI-generated PRs Server #24746: Pull request #18406 opened by ngxson
13m 34s ngxson:xsn/mtmd_ai_gen_pr
ngxson:xsn/mtmd_ai_gen_pr
13m 34s
llama_fit_params: return enum for fail vs. error (#18374) Server #24745: Commit a52dc60 pushed by JohannesGaessler
30m 50s master
master
30m 50s
llama-fit-params: fix Gemma 3 calculation (#18372) Server #24744: Commit 9045c9a pushed by JohannesGaessler
15m 7s master
master
15m 7s
implement adaptive-p sampler Server #24743: Pull request #17927 synchronize by ddh0
27m 50s ddh0:power-law-sampler
ddh0:power-law-sampler
27m 50s
add model: Qwen3-Omni-30B-A3B-Instruct Server #24742: Pull request #18404 opened by TrevorS
12m 59s TrevorS:feature/qwen3-omni
TrevorS:feature/qwen3-omni
12m 59s
vulkan: extend topk_moe to handle sigmoid w/exp_probs_b for nemotron Server #24741: Pull request #18295 synchronize by jeffbolznv
18m 2s jeffbolznv:topk_moe_sigmoid_bias
jeffbolznv:topk_moe_sigmoid_bias
18m 2s
implement adaptive-p sampler Server #24740: Pull request #17927 synchronize by ddh0
12m 41s ddh0:power-law-sampler
ddh0:power-law-sampler
12m 41s
vulkan: extend topk_moe to handle sigmoid w/exp_probs_b for nemotron Server #24739: Pull request #18295 synchronize by jeffbolznv
12m 38s jeffbolznv:topk_moe_sigmoid_bias
jeffbolznv:topk_moe_sigmoid_bias
12m 38s
vulkan: extend topk_moe to handle sigmoid w/exp_probs_b for nemotron Server #24738: Pull request #18295 synchronize by jeffbolznv
12m 41s jeffbolznv:topk_moe_sigmoid_bias
jeffbolznv:topk_moe_sigmoid_bias
12m 41s
vulkan: extend topk_moe to handle sigmoid w/exp_probs_b for nemotron Server #24737: Pull request #18295 synchronize by jeffbolznv
12m 41s jeffbolznv:topk_moe_sigmoid_bias
jeffbolznv:topk_moe_sigmoid_bias
12m 41s