Skip to content

Actions: ngxson/llama.cpp

Actions

CI

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
build.yml
922 workflow run results
922 workflow run results

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

llama-bench : Add --override-tensors arg (#12922) CI #1276: Commit c0a97b7 pushed by ngxson
42m 56s master
master
42m 56s
llama-chat : fix wrong template in GLM4-0414 (#13140) CI #1275: Commit ced44be pushed by ngxson
43m 41s master
master
43m 41s
musa: fix build warning (#13129) CI #1274: Commit e291450 pushed by ngxson
45m 35s master
master
45m 35s
Fixes Qwen2.5VL segfault during inference with https://github.com/ggm… CI #1273: Commit 59e991c pushed by ngxson
50m 40s master
master
50m 40s
clip : Add Qwen2.5VL support (#12402) CI #1272: Commit ca2bb89 pushed by ngxson
43m 18s master
master
43m 18s
common : add common_remote_get_content (#13123) CI #1271: Commit 2d451c8 pushed by ngxson
44m 42s master
master
44m 42s
clip : improve projector naming (#13118) CI #1270: Commit 4753791 pushed by ngxson
54m 27s master
master
54m 27s
ggml: move fp16/bf16 conversion optimizations to CPU backend + export… CI #1269: Commit 77d5e9a pushed by ngxson
49m 15s master
master
49m 15s
common : add common_remote_get_content CI #1268: Commit e6c4319 pushed by ngxson
44m 19s master
master
44m 19s
grammar : handle maxItems == 0 in JSON schema (#13117) CI #1267: Commit d5fe4e8 pushed by ngxson
53m 33s master
master
53m 33s
llama : fix K-shift with quantized K and BLAS backend (#13113) CI #1266: Commit 295354e pushed by ngxson
52m 50s master
master
52m 50s
Force FP32 compute in GLM4 FFN Down (#13101) CI #1265: Commit 558a764 pushed by ngxson
53m 24s master
master
53m 24s
clip : fix pixtral on some GPU backends (#13097) CI #1264: Commit edb18b6 pushed by ngxson
49m 12s master
master
49m 12s
change the reorder tensor from init to execute OP (#13003) CI #1263: Commit 514c456 pushed by ngxson
48m 52s master
master
48m 52s
rpc : do not wait for response when sending RPC_CMD_SET_TENSOR (#12943) CI #1262: Commit 553a5c3 pushed by ngxson
51m 57s master
master
51m 57s
clip : remove boi/eoi embeddings for GLM-edge model (#13081) CI #1261: Commit 13be08d pushed by ngxson
44m 13s master
master
44m 13s
embeddings : fix batch sizes (#13076) CI #1260: Commit 226251e pushed by ngxson
45m 24s master
master
45m 24s
ggml : fix trailing whitespaces (#0) CI #1259: Commit 87616f0 pushed by ngxson
52m 49s master
master
52m 49s
CUDA: use switch statements in constexpr functions (#13095) CI #1258: Commit b10d8bf pushed by ngxson
55m 5s master
master
55m 5s
cmake : do not include ./src as public for libllama (#13062) CI #1257: Commit 13b4548 pushed by ngxson
41m 53s master
master
41m 53s
arg : add --no-mmproj-offload (#13093) CI #1256: Commit 7c727fb pushed by ngxson
43m 42s master
master
43m 42s
arg : clean up handling --mmproj with -hf (#13082) CI #1255: Commit 80982e8 pushed by ngxson
43m 26s master
master
43m 26s
metal : fix floating-point range of attention scores in FA kernels (#… CI #1254: Commit 7604a7d pushed by ngxson
46m 44s master
master
46m 44s
vulkan: matmul gcn tuning (#13016) CI #1253: Commit b3b6d86 pushed by ngxson
55m 48s master
master
55m 48s
llama-mtmd-cli: Sigint rework in mtmd vision example (#13080) CI #1252: Commit 5630406 pushed by ngxson
56m 34s master
master
56m 34s