Skip to content

Actions: ggml-org/llama.cpp

Actions

All workflows

Actions

Loading...
Loading

Showing runs from all workflows
50,349 workflow run results
50,349 workflow run results

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

Vulkan: Add Integer Dot Product mul_mat_vec shader for legacy quants Pull Request Labeler #14271: Pull request #14903 synchronize by 0cc4m
10s
10s
vulkan: use q8_1_x4 blocks in mul_mmq shader Update Operations Documentation #47: Commit c19ec8f pushed by 0cc4m
9s 0cc4m/vulkan-mmq-dp4a-vec
0cc4m/vulkan-mmq-dp4a-vec
9s
vulkan: use q8_1_x4 blocks in mul_mmq shader Python Type-Check #3695: Commit c19ec8f pushed by 0cc4m
1m 34s 0cc4m/vulkan-mmq-dp4a-vec
0cc4m/vulkan-mmq-dp4a-vec
1m 34s
vulkan: use q8_1_x4 blocks in mul_mmq shader Python check requirements.txt #3909: Commit c19ec8f pushed by 0cc4m
3m 19s 0cc4m/vulkan-mmq-dp4a-vec
0cc4m/vulkan-mmq-dp4a-vec
3m 19s
CUDA: use mma FA kernel for gqa > 4 on RTX 4000 CI #25624: Pull request #15035 opened by JohannesGaessler
56m 27s JohannesGaessler:cuda-fa-kernel-choice
JohannesGaessler:cuda-fa-kernel-choice
56m 27s
CUDA: use mma FA kernel for gqa > 4 on RTX 4000 Pull Request Labeler #14270: Pull request #15035 opened by JohannesGaessler
12s
12s
CUDA: use mma FA kernel for gqa > 4 on RTX 4000 EditorConfig Checker #28769: Pull request #15035 opened by JohannesGaessler
21s JohannesGaessler:cuda-fa-kernel-choice
JohannesGaessler:cuda-fa-kernel-choice
21s
CUDA: use mma FA kernel for gqa > 4 on RTX 4000 Server #17030: Pull request #15035 opened by JohannesGaessler
18m 2s JohannesGaessler:cuda-fa-kernel-choice
JohannesGaessler:cuda-fa-kernel-choice
18m 2s
Om 🍉 Pull Request Labeler #14269: Pull request #15033 opened by omroy07
43s
43s
ci : check that pre-tokenizer hashes are up-to-date Python check requirements.txt #3908: Pull request #15032 opened by CISC
4m 43s cisc/ci-pre-tokenizer-hashes
cisc/ci-pre-tokenizer-hashes
4m 43s
ci : check that pre-tokenizer hashes are up-to-date Python Type-Check #3694: Pull request #15032 opened by CISC
2m 25s cisc/ci-pre-tokenizer-hashes
cisc/ci-pre-tokenizer-hashes
2m 25s
ci : check that pre-tokenizer hashes are up-to-date flake8 Lint #19044: Pull request #15032 opened by CISC
1m 40s cisc/ci-pre-tokenizer-hashes
cisc/ci-pre-tokenizer-hashes
1m 40s
ci : check that pre-tokenizer hashes are up-to-date Check Pre-Tokenizer Hashes #1: Pull request #15032 opened by CISC
1m 26s cisc/ci-pre-tokenizer-hashes
cisc/ci-pre-tokenizer-hashes
1m 26s
ci : check that pre-tokenizer hashes are up-to-date EditorConfig Checker #28768: Pull request #15032 opened by CISC
1m 24s cisc/ci-pre-tokenizer-hashes
cisc/ci-pre-tokenizer-hashes
1m 24s
ci : check that pre-tokenizer hashes are up-to-date Pull Request Labeler #14268: Pull request #15032 opened by CISC
15s
15s
add --check-missing parameter Python Type-Check #3693: Commit 4e6b884 pushed by CISC
6m 42s cisc/ci-pre-tokenizer-hashes
cisc/ci-pre-tokenizer-hashes
6m 42s
add --check-missing parameter Python check requirements.txt #3907: Commit 4e6b884 pushed by CISC
5m 31s cisc/ci-pre-tokenizer-hashes
cisc/ci-pre-tokenizer-hashes
5m 31s
torch is not required for convert_hf_to_gguf_update Python Type-Check #3692: Commit 92979ea pushed by CISC
3m 56s cisc/ci-pre-tokenizer-hashes
cisc/ci-pre-tokenizer-hashes
3m 56s
torch is not required for convert_hf_to_gguf_update Python check requirements.txt #3906: Commit 92979ea pushed by CISC
6m 13s cisc/ci-pre-tokenizer-hashes
cisc/ci-pre-tokenizer-hashes
6m 13s
convert : fix Qwen3-Embedding pre-tokenizer hash (#15030) flake8 Lint #19043: Commit 711d5e6 pushed by CISC
1m 48s master
master
1m 48s
convert : fix Qwen3-Embedding pre-tokenizer hash (#15030) Python check requirements.txt #3905: Commit 711d5e6 pushed by CISC
4m 27s master
master
4m 27s
convert : fix Qwen3-Embedding pre-tokenizer hash (#15030) EditorConfig Checker #28767: Commit 711d5e6 pushed by CISC
4m 44s master
master
4m 44s
convert : fix Qwen3-Embedding pre-tokenizer hash (#15030) Python Type-Check #3691: Commit 711d5e6 pushed by CISC
5m 2s master
master
5m 2s
support GLM-4.5 MoE models EditorConfig Checker #28766: Pull request #15026 synchronize by ddh0
8m 47s ddh0:glm45
ddh0:glm45
8m 47s
support GLM-4.5 MoE models Python Type-Check #3690: Pull request #15026 synchronize by ddh0
9m 43s ddh0:glm45
ddh0:glm45
9m 43s
ProTip! You can narrow down the results and go further in time using created:<2025-08-02 or the other filters available.