Skip to content

Actions: ggml-org/llama.cpp

Actions

All workflows

Actions

Loading...
Loading

Showing runs from all workflows
32,245 workflow run results
32,245 workflow run results

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

ggml: move fp16/bf16 conversion optimizations to CPU backend + export conversion APIs Server #13158: Pull request #13107 synchronize by SongXiaoXi
10m 44s SongXiaoXi:master
SongXiaoXi:master
10m 44s
ggml: move fp16/bf16 conversion optimizations to CPU backend + export conversion APIs Pull Request Labeler #10470: Pull request #13107 synchronize by SongXiaoXi
1m 10s
1m 10s
context : allow cache-less context for embeddings Server #13157: Pull request #13108 opened by ggerganov
13m 47s gg/embeddings-no-kv
gg/embeddings-no-kv
13m 47s
context : allow cache-less context for embeddings Pull Request Labeler #10469: Pull request #13108 opened by ggerganov
1m 34s
1m 34s
context : allow cache-less context for embeddings CI #21788: Pull request #13108 opened by ggerganov
24m 15s gg/embeddings-no-kv
gg/embeddings-no-kv
24m 15s
ggml: move fp16/bf16 conversion optimizations to CPU backend + export conversion APIs EditorConfig Checker #24430: Pull request #13107 opened by SongXiaoXi
2m 34s SongXiaoXi:master
SongXiaoXi:master
2m 34s
ggml: move fp16/bf16 conversion optimizations to CPU backend + export conversion APIs CI #21787: Pull request #13107 opened by SongXiaoXi
19m 33s SongXiaoXi:master
SongXiaoXi:master
19m 33s
ggml: move fp16/bf16 conversion optimizations to CPU backend + export conversion APIs Server #13156: Pull request #13107 opened by SongXiaoXi
18m 27s SongXiaoXi:master
SongXiaoXi:master
18m 27s
ggml: move fp16/bf16 conversion optimizations to CPU backend + export conversion APIs Pull Request Labeler #10468: Pull request #13107 opened by SongXiaoXi
2m 46s
2m 46s
llama-bench: add -d depth arg Pull Request Labeler #10467: Pull request #13096 synchronize by thevishalagarwal
3m 4s
3m 4s
llama : try loading tensors with pre-computed hashes EditorConfig Checker #24428: Pull request #13106 opened by rgerganov
8m 10s rgerganov:rpc-load-tensor
rgerganov:rpc-load-tensor
8m 10s
llama : try loading tensors with pre-computed hashes CI #21785: Pull request #13106 opened by rgerganov
48m 1s rgerganov:rpc-load-tensor
rgerganov:rpc-load-tensor
48m 1s
llama : try loading tensors with pre-computed hashes Server #13154: Pull request #13106 opened by rgerganov
14m 4s rgerganov:rpc-load-tensor
rgerganov:rpc-load-tensor
14m 4s
llama : try loading tensors with pre-computed hashes Pull Request Labeler #10466: Pull request #13106 opened by rgerganov
3m 5s
3m 5s
Force FP32 compute in GLM4 FFN Down EditorConfig Checker #24427: Pull request #13101 synchronize by city96
44s city96:glm4_cublas_fix
city96:glm4_cublas_fix
44s
Force FP32 compute in GLM4 FFN Down Server #13153: Pull request #13101 synchronize by city96
17m 18s city96:glm4_cublas_fix
city96:glm4_cublas_fix
17m 18s
Force FP32 compute in GLM4 FFN Down CI #21784: Pull request #13101 synchronize by city96
1h 8m 11s city96:glm4_cublas_fix
city96:glm4_cublas_fix
1h 8m 11s
Force FP32 compute in GLM4 FFN Down Pull Request Labeler #10465: Pull request #13101 synchronize by city96
21s
21s
kv-cache : separate recurrent vs non-recurrent impl Server #13152: Pull request #12799 synchronize by ggerganov
8m 38s gg/llama-kv-cache-v6
gg/llama-kv-cache-v6
8m 38s
kv-cache : separate recurrent vs non-recurrent impl CI #21783: Pull request #12799 synchronize by ggerganov
47m 17s gg/llama-kv-cache-v6
gg/llama-kv-cache-v6
47m 17s
kv-cache : separate recurrent vs non-recurrent impl EditorConfig Checker #24426: Pull request #12799 synchronize by ggerganov
33s gg/llama-kv-cache-v6
gg/llama-kv-cache-v6
33s
kv-cache : separate recurrent vs non-recurrent impl Pull Request Labeler #10464: Pull request #12799 synchronize by ggerganov
29s
29s
kv-cache : separate recurrent vs non-recurrent impl EditorConfig Checker #24425: Pull request #12799 synchronize by ggerganov
2m 7s gg/llama-kv-cache-v6
gg/llama-kv-cache-v6
2m 7s
kv-cache : separate recurrent vs non-recurrent impl Server #13151: Pull request #12799 synchronize by ggerganov
14m 23s gg/llama-kv-cache-v6
gg/llama-kv-cache-v6
14m 23s
kv-cache : separate recurrent vs non-recurrent impl CI #21782: Pull request #12799 synchronize by ggerganov
19m 28s gg/llama-kv-cache-v6
gg/llama-kv-cache-v6
19m 28s
ProTip! You can narrow down the results and go further in time using created:<2025-04-25 or the other filters available.