Skip to content

Actions: ngxson/llama.cpp

Actions

All workflows

Actions

Loading...
Loading

Showing runs from all workflows
3,880 workflow run results
3,880 workflow run results

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

llama : gemma3 : use output tensor if it exists in model weight (#12506) Python Type-Check #331: Commit fbdfefe pushed by ngxson
1m 51s master
master
1m 51s
llama : gemma3 : use output tensor if it exists in model weight (#12506) Server #1179: Commit fbdfefe pushed by ngxson
8m 15s master
master
8m 15s
llama : gemma3 : use output tensor if it exists in model weight (#12506) flake8 Lint #1236: Commit fbdfefe pushed by ngxson
15s master
master
15s
llama : gemma3 : use output tensor if it exists in model weight (#12506) EditorConfig Checker #1275: Commit fbdfefe pushed by ngxson
15s master
master
15s
llama : gemma3 : use output tensor if it exists in model weight (#12506) CI #1060: Commit fbdfefe pushed by ngxson
42m 14s master
master
42m 14s
ggml : fix quantized cpy op (#12310) CI #1059: Commit ba932df pushed by ngxson
47m 9s master
master
47m 9s
ggml : fix quantized cpy op (#12310) Server #1178: Commit ba932df pushed by ngxson
8m 53s master
master
8m 53s
ggml : fix quantized cpy op (#12310) EditorConfig Checker #1274: Commit ba932df pushed by ngxson
16s master
master
16s
musa: refine compute capability (#12493) EditorConfig Checker #1273: Commit fac63a3 pushed by ngxson
18s master
master
18s
musa: refine compute capability (#12493) Server #1177: Commit fac63a3 pushed by ngxson
7m 53s master
master
7m 53s
musa: refine compute capability (#12493) CI #1058: Commit fac63a3 pushed by ngxson
52m 46s master
master
52m 46s
vulkan: Optimize mul_mat_vec p021 and nc shaders (#12505) EditorConfig Checker #1272: Commit eddfb43 pushed by ngxson
16s master
master
16s
vulkan: Optimize mul_mat_vec p021 and nc shaders (#12505) Server #1176: Commit eddfb43 pushed by ngxson
8m 15s master
master
8m 15s
vulkan: Optimize mul_mat_vec p021 and nc shaders (#12505) CI #1057: Commit eddfb43 pushed by ngxson
49m 30s master
master
49m 30s
Publish Docker image Publish Docker image #655: Scheduled
51m 51s master
master
51m 51s
Close inactive issues Close inactive issues #368: Scheduled
12s master
master
12s
llama : gemma3 : use output tensor if it exists in model weight Python Type-Check #330: Commit 9a49ae9 pushed by ngxson
1m 19s xsn/gemma3_lm_head
xsn/gemma3_lm_head
1m 19s
Vulkan: RTE rounding for cpy to quant (#12480) CI #1056: Commit 4375415 pushed by ngxson
52m 18s master
master
52m 18s
Vulkan: RTE rounding for cpy to quant (#12480) Server #1175: Commit 4375415 pushed by ngxson
11m 20s master
master
11m 20s
Vulkan: RTE rounding for cpy to quant (#12480) EditorConfig Checker #1271: Commit 4375415 pushed by ngxson
3m 52s master
master
3m 52s
vulkan: workaround for AMD Windows driver 16 bit unpack8 bug (#12472) CI #1055: Commit 30c42ef pushed by ngxson
44m 49s master
master
44m 49s
vulkan: workaround for AMD Windows driver 16 bit unpack8 bug (#12472) EditorConfig Checker #1270: Commit 30c42ef pushed by ngxson
19s master
master
19s
qwen 0.6b kinda work Python check requirements.txt #225: Commit 56b5a07 pushed by ngxson
2m 52s xsn/qwen3
xsn/qwen3
2m 52s
qwen 0.6b kinda work Python Type-Check #329: Commit 56b5a07 pushed by ngxson
1m 12s xsn/qwen3
xsn/qwen3
1m 12s
Private batch API (for AI review) flake8 Lint #1235: Pull request #14 synchronize by ngxson
23s xsn/private_batch_api
xsn/private_batch_api
23s