Skip to content

Actions: ggml-org/llama.cpp

Actions

All workflows

Actions

Loading...
Loading

Showing runs from all workflows
54,415 workflow run results
54,415 workflow run results

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

llama: use FA + max. GPU layers by default Server #17678: Pull request #15434 opened by JohannesGaessler
11m 13s JohannesGaessler:llama-update-defaults
JohannesGaessler:llama-update-defaults
11m 13s
llama: use FA + max. GPU layers by default EditorConfig Checker #29540: Pull request #15434 opened by JohannesGaessler
19s JohannesGaessler:llama-update-defaults
JohannesGaessler:llama-update-defaults
19s
llama: use FA + max. GPU layers by default flake8 Lint #19212: Pull request #15434 opened by JohannesGaessler
20s JohannesGaessler:llama-update-defaults
JohannesGaessler:llama-update-defaults
20s
llama: use FA + max. GPU layers by default Python Type-Check #3884: Pull request #15434 opened by JohannesGaessler
1m 37s JohannesGaessler:llama-update-defaults
JohannesGaessler:llama-update-defaults
1m 37s
llama: use FA + max. GPU layers by default Pull Request Labeler #14960: Pull request #15434 opened by JohannesGaessler
12s
12s
convert : handle pre-quantized models EditorConfig Checker #29539: Pull request #14810 synchronize by compilade
21s compilade/convert-prequant
compilade/convert-prequant
21s
convert : handle pre-quantized models Pull Request Labeler #14959: Pull request #14810 synchronize by compilade
10s
10s
convert : handle pre-quantized models flake8 Lint #19211: Pull request #14810 synchronize by compilade
19s compilade/convert-prequant
compilade/convert-prequant
19s
convert : handle pre-quantized models Check Pre-Tokenizer Hashes #128: Pull request #14810 synchronize by compilade
32s compilade/convert-prequant
compilade/convert-prequant
32s
convert : handle pre-quantized models Python Type-Check #3883: Pull request #14810 synchronize by compilade
1m 42s compilade/convert-prequant
compilade/convert-prequant
1m 42s
convert : handle pre-quantized models Python check requirements.txt #4044: Pull request #14810 synchronize by compilade
3m 40s compilade/convert-prequant
compilade/convert-prequant
3m 40s
convert : fix conversion from FP8 for Deepseek-V3.1-Base Check Pre-Tokenizer Hashes #127: Commit 8993982 pushed by compilade
30s compilade/convert-prequant
compilade/convert-prequant
30s
convert : fix conversion from FP8 for Deepseek-V3.1-Base Python check requirements.txt #4043: Commit 8993982 pushed by compilade
3m 21s compilade/convert-prequant
compilade/convert-prequant
3m 21s
convert : fix conversion from FP8 for Deepseek-V3.1-Base Python Type-Check #3882: Commit 8993982 pushed by compilade
1m 36s compilade/convert-prequant
compilade/convert-prequant
1m 36s
CUDA: replace GGML_CUDA_F16 with CUDA arch checks CI #26265: Pull request #15433 opened by JohannesGaessler
1h 0m 52s JohannesGaessler:cuda-remove-f16
JohannesGaessler:cuda-remove-f16
1h 0m 52s
CUDA: replace GGML_CUDA_F16 with CUDA arch checks EditorConfig Checker #29538: Pull request #15433 opened by JohannesGaessler
19s JohannesGaessler:cuda-remove-f16
JohannesGaessler:cuda-remove-f16
19s
CUDA: replace GGML_CUDA_F16 with CUDA arch checks Server #17677: Pull request #15433 opened by JohannesGaessler
12m 33s JohannesGaessler:cuda-remove-f16
JohannesGaessler:cuda-remove-f16
12m 33s
CUDA: replace GGML_CUDA_F16 with CUDA arch checks Pull Request Labeler #14958: Pull request #15433 opened by JohannesGaessler
11s
11s
vulkan: optimize mxfp4 Pull Request Labeler #14957: Pull request #15363 synchronize by lovedheart
11s
11s
vulkan: shorten pipeline name strings EditorConfig Checker #29536: Pull request #15431 opened by jeffbolznv
18s jeffbolznv:simpler_names
jeffbolznv:simpler_names
18s
vulkan: shorten pipeline name strings Pull Request Labeler #14956: Pull request #15431 opened by jeffbolznv
11s
11s
vulkan: shorten pipeline name strings Server #17676: Pull request #15431 opened by jeffbolznv
11m 55s jeffbolznv:simpler_names
jeffbolznv:simpler_names
11m 55s
vulkan: shorten pipeline name strings CI #26263: Pull request #15431 opened by jeffbolznv
59m 50s jeffbolznv:simpler_names
jeffbolznv:simpler_names
59m 50s
opencl: mark argsort unsupported if cols exceed workgroup limit (#1… CI #26262: Commit fb22dd0 pushed by max-krasnyansky
1h 5m 25s master
master
1h 5m 25s
opencl: mark argsort unsupported if cols exceed workgroup limit (#1… Release #705: Commit fb22dd0 pushed by max-krasnyansky
12m 57s master
master
12m 57s