Skip to content

Actions: ggml-org/llama.cpp

Actions

CI

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
build.yml
2,448 workflow run results
2,448 workflow run results

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

cuda: Use common gfx8 value for GCN4 CI #18259: Pull request #11209 opened by Haus1
25m 44s Haus1:adjust-gcn4-id
Haus1:adjust-gcn4-id
25m 44s
Reset color before we exit (#11205) CI #18258: Commit 924518e pushed by ericcurtin
38m 54s master
master
38m 54s
Reset color before we exit CI #18257: Pull request #11205 opened by ericcurtin
19m 59s color-reset
color-reset
19m 59s
cmake : enable -Wshadow for C++ code CI #18256: Pull request #11193 synchronize by ggerganov
43m 55s gg/llama-shadow-on
gg/llama-shadow-on
43m 55s
cmake : enable -Wshadow for C++ code CI #18255: Pull request #11193 synchronize by ggerganov
23m 1s gg/llama-shadow-on
gg/llama-shadow-on
23m 1s
cmake : enable -Wshadow for C++ code CI #18254: Pull request #11193 synchronize by ggerganov
24m 58s gg/llama-shadow-on
gg/llama-shadow-on
24m 58s
cmake : enable -Wshadow for C++ code CI #18253: Pull request #11193 synchronize by ggerganov
34m 13s gg/llama-shadow-on
gg/llama-shadow-on
34m 13s
cmake : enable -Wshadow for C++ code CI #18252: Pull request #11193 synchronize by ggerganov
1m 20s gg/llama-shadow-on
gg/llama-shadow-on
1m 20s
cmake : enable -Wshadow for C++ code CI #18251: Pull request #11193 synchronize by ggerganov
9m 16s gg/llama-shadow-on
gg/llama-shadow-on
9m 16s
cmake : enable -Wshadow for C++ code CI #18250: Pull request #11193 synchronize by ggerganov
34m 17s gg/llama-shadow-on
gg/llama-shadow-on
34m 17s
main : improve UX for chat mode (to be discussed) CI #18249: Pull request #11203 opened by ngxson
43m 33s ngxson:xsn/chat_cli
ngxson:xsn/chat_cli
43m 33s
cmake : enable -Wshadow for C++ code CI #18248: Pull request #11193 synchronize by ggerganov
18m 13s gg/llama-shadow-on
gg/llama-shadow-on
18m 13s
llama : fix chat template gguf key (#11201) CI #18247: Commit 9a48399 pushed by ngxson
1h 8m 50s master
master
1h 8m 50s
cmake : enable -Wshadow for C++ code CI #18246: Pull request #11193 synchronize by ggerganov
36m 41s gg/llama-shadow-on
gg/llama-shadow-on
36m 41s
llama : fix chat template gguf key CI #18245: Pull request #11201 opened by ngxson
25m 8s ngxson:xsn/fix_chat_tmpl
ngxson:xsn/fix_chat_tmpl
25m 8s
cmake : enable -Wshadow for C++ code CI #18244: Pull request #11193 synchronize by ggerganov
10m 20s gg/llama-shadow-on
gg/llama-shadow-on
10m 20s
llama : remove notion of CLS token (#11064) CI #18243: Commit 08f10f6 pushed by ggerganov
38m 16s master
master
38m 16s
llama : remove notion of CLS token CI #18242: Pull request #11064 synchronize by ggerganov
26m 8s gg/llama-refactor-5
gg/llama-refactor-5
26m 8s
llama : remove notion of CLS token CI #18241: Pull request #11064 synchronize by ggerganov
2m 22s gg/llama-refactor-5
gg/llama-refactor-5
2m 22s
llama : add llama_vocab, functions -> methods, naming CI #18240: Pull request #11110 synchronize by ggerganov
19m 35s gg/llama-refactor-7
gg/llama-refactor-7
19m 35s
fix: ggml: fix vulkan-shaders-gen build CI #18239: Pull request #10448 synchronize by sparkleholic
21m 28s sparkleholic:master_fix
sparkleholic:master_fix
21m 28s
ggml-cuda : add TQ2_0 kernels, for ternary inference on GPU CI #18238: Pull request #11183 synchronize by compilade
42m 4s compilade/cuda-tq2_0
compilade/cuda-tq2_0
42m 4s
fix: ggml: fix vulkan-shaders-gen build CI #18237: Pull request #10448 synchronize by sparkleholic
29m 17s sparkleholic:master_fix
sparkleholic:master_fix
29m 17s
common : support tag-based --hf-repo like on ollama CI #18236: Pull request #11195 synchronize by ngxson
25m 4s ngxson:xsn/tag_based_hf_repo
ngxson:xsn/tag_based_hf_repo
25m 4s
common : support tag-based --hf-repo like on ollama CI #18235: Pull request #11195 synchronize by ngxson
31m 46s ngxson:xsn/tag_based_hf_repo
ngxson:xsn/tag_based_hf_repo
31m 46s