Skip to content

Actions: ggml-org/llama.cpp

Actions

Server

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
server.yml
11,777 workflow runs
11,777 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

Support jinja extra template kwargs (Qwen3 enable_thinking feature), from command line and from client Server #13331: Pull request #13196 synchronize by matteoserva
April 30, 2025 15:56 2m 2s matteoserva:enable_thinking
matteoserva:enable_thinking
April 30, 2025 15:56 2m 2s
rpc: avoid uninitialized memory in serialize_tensor Server #13330: Pull request #13210 opened by justinsb
April 30, 2025 13:35 15m 24s justinsb:avoid_sending_uninitialized_memory
justinsb:avoid_sending_uninitialized_memory
April 30, 2025 13:35 15m 24s
llava : remove duplicate include (#13207) Server #13329: Commit ceda28e pushed by CISC
April 30, 2025 13:25 34m 28s master
master
April 30, 2025 13:25 34m 28s
kv-cache : separate recurrent vs non-recurrent impl Server #13328: Pull request #12799 synchronize by ggerganov
April 30, 2025 13:14 15m 12s gg/llama-kv-cache-v6
gg/llama-kv-cache-v6
April 30, 2025 13:14 15m 12s
kv-cache : separate recurrent vs non-recurrent impl Server #13327: Pull request #12799 synchronize by ggerganov
April 30, 2025 13:04 10m 10s gg/llama-kv-cache-v6
gg/llama-kv-cache-v6
April 30, 2025 13:04 10m 10s
kv-cache : separate recurrent vs non-recurrent impl Server #13326: Pull request #12799 synchronize by ggerganov
April 30, 2025 12:55 8m 35s gg/llama-kv-cache-v6
gg/llama-kv-cache-v6
April 30, 2025 12:55 8m 35s
common : add -jf / --json-schema-file flag (#12011) Server #13325: Commit 3b127c7 pushed by CISC
April 30, 2025 12:52 17m 45s master
master
April 30, 2025 12:52 17m 45s
kv-cache : separate recurrent vs non-recurrent impl Server #13324: Pull request #12799 synchronize by ggerganov
April 30, 2025 12:50 4m 51s gg/llama-kv-cache-v6
gg/llama-kv-cache-v6
April 30, 2025 12:50 4m 51s
ggml : fix ppc64le build (#13176) Server #13323: Commit 4163137 pushed by slaren
April 30, 2025 11:17 18m 28s master
master
April 30, 2025 11:17 18m 28s
examples: remove the unnecessary include Server #13322: Pull request #13207 opened by tattn
April 30, 2025 10:51 41m 9s tattn:patch-2
tattn:patch-2
April 30, 2025 10:51 41m 9s
feat(ggml-cpu): enable z17 compile (#13182) Server #13321: Commit 44cd8d9 pushed by ericcurtin
April 30, 2025 09:47 13m 51s master
master
April 30, 2025 09:47 13m 51s
docker : do not build tests (#13204) Server #13320: Commit da84c04 pushed by ngxson
April 30, 2025 08:44 16m 21s master
master
April 30, 2025 08:44 16m 21s
kv-cache : separate recurrent vs non-recurrent impl Server #13319: Pull request #12799 synchronize by ggerganov
April 30, 2025 08:30 8m 47s gg/llama-kv-cache-v6
gg/llama-kv-cache-v6
April 30, 2025 08:30 8m 47s
docker : do not build tests Server #13318: Pull request #13204 synchronize by ngxson
April 30, 2025 08:30 8m 49s ngxson:xsn/docker_no_build_test
ngxson:xsn/docker_no_build_test
April 30, 2025 08:30 8m 49s
kv-cache : separate recurrent vs non-recurrent impl Server #13317: Pull request #12799 synchronize by ggerganov
April 30, 2025 08:24 6m 12s gg/llama-kv-cache-v6
gg/llama-kv-cache-v6
April 30, 2025 08:24 6m 12s
Support jinja extra template kwargs (Qwen3 enable_thinking feature), from command line and from client Server #13316: Pull request #13196 synchronize by matteoserva
April 30, 2025 07:34 11m 55s matteoserva:enable_thinking
matteoserva:enable_thinking
April 30, 2025 07:34 11m 55s
kv-cache : separate recurrent vs non-recurrent impl Server #13315: Pull request #12799 synchronize by ggerganov
April 30, 2025 07:22 11m 42s gg/llama-kv-cache-v6
gg/llama-kv-cache-v6
April 30, 2025 07:22 11m 42s
kv-cache : separate recurrent vs non-recurrent impl Server #13314: Pull request #12799 synchronize by ggerganov
April 30, 2025 07:15 7m 51s gg/llama-kv-cache-v6
gg/llama-kv-cache-v6
April 30, 2025 07:15 7m 51s
kv-cache : separate recurrent vs non-recurrent impl Server #13313: Pull request #12799 synchronize by ggerganov
April 30, 2025 07:12 2m 45s gg/llama-kv-cache-v6
gg/llama-kv-cache-v6
April 30, 2025 07:12 2m 45s
rpc : fix cache directory initialization (#13188) Server #13312: Commit a0f7016 pushed by rgerganov
April 30, 2025 06:29 10m 52s master
master
April 30, 2025 06:29 10m 52s
Fix for issue #13170 Server #13311: Pull request #13176 synchronize by shalinib-ibm
April 30, 2025 06:28 12m 52s shalinib-ibm:main_br
shalinib-ibm:main_br
April 30, 2025 06:28 12m 52s
arg : allow using -hf offline Server #13310: Pull request #13202 opened by ngxson
April 29, 2025 22:40 8m 24s ngxson:xsn/hf_offline
ngxson:xsn/hf_offline
April 29, 2025 22:40 8m 24s
CUDA: batched+noncont MMQ, refactor bs>1 MoE code Server #13309: Pull request #13199 opened by JohannesGaessler
April 29, 2025 20:34 8m 33s JohannesGaessler:cuda-moe-mmq-5
JohannesGaessler:cuda-moe-mmq-5
April 29, 2025 20:34 8m 33s
Support jinja extra template kwargs (Qwen3 enable_thinking feature), from command line and from client Server #13308: Pull request #13196 synchronize by matteoserva
April 29, 2025 19:08 8m 49s matteoserva:enable_thinking
matteoserva:enable_thinking
April 29, 2025 19:08 8m 49s
Support jinja extra template kwargs (Qwen3 enable_thinking feature), from command line and from client Server #13307: Pull request #13196 synchronize by matteoserva
April 29, 2025 19:03 5m 36s matteoserva:enable_thinking
matteoserva:enable_thinking
April 29, 2025 19:03 5m 36s