Skip to content

Actions: ggml-org/llama.cpp

Actions

All workflows

Actions

Loading...
Loading

Showing runs from all workflows
34,344 workflow run results
34,344 workflow run results

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

Add --no-op-offload to improve -ot pp perf in MoE models like llama4 400B Server #13662: Pull request #13386 opened by hjc4869
1h 18m 7s hjc4869:no_op_offload
hjc4869:no_op_offload
1h 18m 7s
Add --no-op-offload to improve -ot pp perf in MoE models like llama4 400B CI #22302: Pull request #13386 opened by hjc4869
2h 47m 28s hjc4869:no_op_offload
hjc4869:no_op_offload
2h 47m 28s
Add --no-op-offload to improve -ot pp perf in MoE models like llama4 400B EditorConfig Checker #25002: Pull request #13386 opened by hjc4869
16m 12s hjc4869:no_op_offload
hjc4869:no_op_offload
16m 12s
Add --no-op-offload to improve -ot pp perf in MoE models like llama4 400B Pull Request Labeler #10952: Pull request #13386 opened by hjc4869
46m 0s
46m 0s
arg : add model catalog CI #22301: Pull request #13385 opened by ngxson
1h 58m 1s ngxson:xsn/arg_add_catalog
ngxson:xsn/arg_add_catalog
1h 58m 1s
arg : add model catalog EditorConfig Checker #25001: Pull request #13385 opened by ngxson
46m 44s ngxson:xsn/arg_add_catalog
ngxson:xsn/arg_add_catalog
46m 44s
arg : add model catalog Server #13661: Pull request #13385 opened by ngxson
58m 33s ngxson:xsn/arg_add_catalog
ngxson:xsn/arg_add_catalog
58m 33s
arg : add model catalog Pull Request Labeler #10951: Pull request #13385 opened by ngxson
47m 45s
47m 45s
kv-cache : add SWA support EditorConfig Checker #25000: Pull request #13194 synchronize by ggerganov
41m 58s gg/swa
gg/swa
41m 58s
kv-cache : add SWA support CI #22300: Pull request #13194 synchronize by ggerganov
2h 33m 41s gg/swa
gg/swa
2h 33m 41s
kv-cache : add SWA support Server #13660: Pull request #13194 synchronize by ggerganov
51m 23s gg/swa
gg/swa
51m 23s
kv-cache : add SWA support Pull Request Labeler #10950: Pull request #13194 synchronize by ggerganov
36m 17s
36m 17s
kv-cache : prepare for SWA (wip) Python check requirements.txt #3055: Commit 1c69466 pushed by ggerganov
10m 58s gg/swa
gg/swa
10m 58s
kv-cache : prepare for SWA (wip) Python Type-Check #2575: Commit 1c69466 pushed by ggerganov
52m 51s gg/swa
gg/swa
52m 51s
ggml-cpu: Integrate fp32=bf16xbf16 SME KleidiAI kernel Server #13659: Pull request #13053 synchronize by eddnjjn
44m 13s eddnjjn:feature/fp32_sme_kernel
eddnjjn:feature/fp32_sme_kernel
44m 13s
ggml-cpu: Integrate fp32=bf16xbf16 SME KleidiAI kernel CI #22299: Pull request #13053 synchronize by eddnjjn
2h 18m 40s eddnjjn:feature/fp32_sme_kernel
eddnjjn:feature/fp32_sme_kernel
2h 18m 40s
ggml-cpu: Integrate fp32=bf16xbf16 SME KleidiAI kernel EditorConfig Checker #24999: Pull request #13053 synchronize by eddnjjn
7m 10s eddnjjn:feature/fp32_sme_kernel
eddnjjn:feature/fp32_sme_kernel
7m 10s
ggml-cpu: Integrate fp32=bf16xbf16 SME KleidiAI kernel Pull Request Labeler #10949: Pull request #13053 synchronize by eddnjjn
12m 39s
12m 39s
CUDA: fix crash on large batch size for MoE models CI #22298: Pull request #13384 opened by JohannesGaessler
1h 51m 50s JohannesGaessler:cuda-fix-moe-max-ub
JohannesGaessler:cuda-fix-moe-max-ub
1h 51m 50s
CUDA: fix crash on large batch size for MoE models EditorConfig Checker #24998: Pull request #13384 opened by JohannesGaessler
15m 18s JohannesGaessler:cuda-fix-moe-max-ub
JohannesGaessler:cuda-fix-moe-max-ub
15m 18s
CUDA: fix crash on large batch size for MoE models Server #13658: Pull request #13384 opened by JohannesGaessler
39m 57s JohannesGaessler:cuda-fix-moe-max-ub
JohannesGaessler:cuda-fix-moe-max-ub
39m 57s
CUDA: fix crash on large batch size for MoE models Pull Request Labeler #10948: Pull request #13384 opened by JohannesGaessler
15m 29s
15m 29s
vulkan: scalar flash attention implementation CI #22297: Pull request #13324 synchronize by jeffbolznv
1h 27m 40s jeffbolznv:scalar_fa_3
jeffbolznv:scalar_fa_3
1h 27m 40s
vulkan: scalar flash attention implementation Pull Request Labeler #10947: Pull request #13324 synchronize by jeffbolznv
18m 28s
18m 28s
vulkan: scalar flash attention implementation EditorConfig Checker #24997: Pull request #13324 synchronize by jeffbolznv
19m 8s jeffbolznv:scalar_fa_3
jeffbolznv:scalar_fa_3
19m 8s