Skip to content

Actions: ggml-org/llama.cpp

Actions

All workflows

Actions

Loading...
Loading

Showing runs from all workflows
60,386 workflow run results
60,386 workflow run results

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

64 bit CUDA copy routines via GGML_CUDA_ALLOW_LARGE_TENSORS CI #27323: Pull request #15298 synchronize by createthis
2h 24m 1s createthis:fix_131k_context_GGML_ASSERT
createthis:fix_131k_context_GGML_ASSERT
2h 24m 1s
64 bit CUDA copy routines via GGML_CUDA_ALLOW_LARGE_TENSORS Build on RISCV Linux Machine by Cloud-V #939: Pull request #15298 synchronize by createthis
8m 3s createthis:fix_131k_context_GGML_ASSERT
createthis:fix_131k_context_GGML_ASSERT
8m 3s
64 bit CUDA copy routines via GGML_CUDA_ALLOW_LARGE_TENSORS EditorConfig Checker #30722: Pull request #15298 synchronize by createthis
14m 19s createthis:fix_131k_context_GGML_ASSERT
createthis:fix_131k_context_GGML_ASSERT
14m 19s
64 bit CUDA copy routines via GGML_CUDA_ALLOW_LARGE_TENSORS Pull Request Labeler #16037: Pull request #15298 synchronize by createthis
27m 52s
27m 52s
convert : use reflinks for faster conversion Server #18751: Pull request #15727 synchronize by compilade
49m 3s compilade/convert-reflinks
compilade/convert-reflinks
49m 3s
convert : use reflinks for faster conversion CI #27322: Pull request #15727 synchronize by compilade
1h 36m 59s compilade/convert-reflinks
compilade/convert-reflinks
1h 36m 59s
convert : use reflinks for faster conversion Python check requirements.txt #4254: Pull request #15727 synchronize by compilade
9m 51s compilade/convert-reflinks
compilade/convert-reflinks
9m 51s
convert : use reflinks for faster conversion Build on RISCV Linux Machine by Cloud-V #938: Pull request #15727 synchronize by compilade
9m 38s compilade/convert-reflinks
compilade/convert-reflinks
9m 38s
convert : use reflinks for faster conversion Python Type-Check #4207: Pull request #15727 synchronize by compilade
22m 30s compilade/convert-reflinks
compilade/convert-reflinks
22m 30s
convert : use reflinks for faster conversion Check Pre-Tokenizer Hashes #304: Pull request #15727 synchronize by compilade
32m 26s compilade/convert-reflinks
compilade/convert-reflinks
32m 26s
convert : use reflinks for faster conversion flake8 Lint #19458: Pull request #15727 synchronize by compilade
39m 50s compilade/convert-reflinks
compilade/convert-reflinks
39m 50s
convert : for FP8, use scale type to decide auto type Python check requirements.txt #4253: Commit 833d03c pushed by compilade
44m 29s compilade/convert-reflinks
compilade/convert-reflinks
44m 29s
convert : for FP8, use scale type to decide auto type Python Type-Check #4206: Commit 833d03c pushed by compilade
17m 32s compilade/convert-reflinks
compilade/convert-reflinks
17m 32s
convert : use reflinks for faster conversion Pull Request Labeler #16036: Pull request #15727 synchronize by compilade
31m 28s
31m 28s
convert : for FP8, use scale type to decide auto type Check Pre-Tokenizer Hashes #303: Commit 833d03c pushed by compilade
34m 3s compilade/convert-reflinks
compilade/convert-reflinks
34m 3s
convert : parse safetensors directly Build on RISCV Linux Machine by Cloud-V #937: Pull request #15667 synchronize by compilade
15m 28s compilade/convert-safetensors-parse
compilade/convert-safetensors-parse
15m 28s
convert : parse safetensors directly Python check requirements.txt #4252: Pull request #15667 synchronize by compilade
17m 52s compilade/convert-safetensors-parse
compilade/convert-safetensors-parse
17m 52s
convert : parse safetensors directly Check Pre-Tokenizer Hashes #302: Pull request #15667 synchronize by compilade
32m 34s compilade/convert-safetensors-parse
compilade/convert-safetensors-parse
32m 34s
convert : parse safetensors directly flake8 Lint #19457: Pull request #15667 synchronize by compilade
33m 56s compilade/convert-safetensors-parse
compilade/convert-safetensors-parse
33m 56s
convert : parse safetensors directly Python Type-Check #4205: Pull request #15667 synchronize by compilade
36m 41s compilade/convert-safetensors-parse
compilade/convert-safetensors-parse
36m 41s
convert : parse safetensors directly Pull Request Labeler #16035: Pull request #15667 synchronize by compilade
28m 13s
28m 13s
convert : fix no-lazy dtypes from direct safetensors Check Pre-Tokenizer Hashes #301: Commit e582f1a pushed by compilade
3m 0s compilade/convert-safetensors-parse
compilade/convert-safetensors-parse
3m 0s
convert : fix no-lazy dtypes from direct safetensors Python check requirements.txt #4251: Commit e582f1a pushed by compilade
9m 3s compilade/convert-safetensors-parse
compilade/convert-safetensors-parse
9m 3s
convert : fix no-lazy dtypes from direct safetensors Python Type-Check #4204: Commit e582f1a pushed by compilade
32m 48s compilade/convert-safetensors-parse
compilade/convert-safetensors-parse
32m 48s
convert : handle pre-quantized models Build on RISCV Linux Machine by Cloud-V #936: Pull request #14810 synchronize by compilade
4m 59s compilade/convert-prequant
compilade/convert-prequant
4m 59s