Skip to content

Actions: ggml-org/llama.cpp

Actions

Pull Request Labeler

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
labeler.yml
14,263 workflow runs
14,263 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

llama-model: fix insonsistent ctxs <-> bufs order Pull Request Labeler #17689: Pull request #16581 synchronize by JohannesGaessler
13s
13s
gguf_convert_endian.py: add support for converting BF16 data Pull Request Labeler #17688: Pull request #16594 opened by AlekseiNikiforovIBM
11s
11s
Model: Qwen3 Next Pull Request Labeler #17687: Pull request #16095 synchronize by pwilkin
3m 46s
3m 46s
Model: Qwen3 Next Pull Request Labeler #17686: Pull request #16095 synchronize by pwilkin
1m 24s
1m 24s
Model: Qwen3 Next Pull Request Labeler #17685: Pull request #16095 synchronize by pwilkin
5m 42s
5m 42s
CPU: Add support for FLOOR,CEIL,ROUND and TRUNC unary operators Pull Request Labeler #17684: Pull request #16083 synchronize by safranowith
6m 0s
6m 0s
llama-quant: add support for mmproj Pull Request Labeler #17683: Pull request #16592 synchronize by ngxson
29m 40s
29m 40s
CUDA: Changing the CUDA scheduling strategy to spin Pull Request Labeler #17682: Pull request #16585 synchronize by JTischbein
43m 20s
43m 20s
CUDA: Changing the CUDA scheduling strategy to spin Pull Request Labeler #17681: Pull request #16585 synchronize by JTischbein
30m 10s
30m 10s
Add server-driven parameter defaults and syncing Pull Request Labeler #17680: Pull request #16515 synchronize by allozaur
34m 26s
34m 26s
llama-quant: add support for mmproj Pull Request Labeler #17679: Pull request #16592 synchronize by ngxson
17m 12s
17m 12s
llama-quant: add support for mmproj Pull Request Labeler #17678: Pull request #16592 synchronize by ngxson
17m 59s
17m 59s
CPU: Add support for FLOOR,CEIL,ROUND and TRUNC unary operators Pull Request Labeler #17677: Pull request #16083 synchronize by safranowith
14m 16s
14m 16s
CUDA: Changing the CUDA scheduling strategy to spin Pull Request Labeler #17676: Pull request #16585 synchronize by JTischbein
36m 39s
36m 39s
llama-quant: add support for mmproj Pull Request Labeler #17675: Pull request #16592 opened by ngxson
20m 44s
20m 44s
server : fix mtmd checkpoints Pull Request Labeler #17674: Pull request #16591 opened by ggerganov
11s
11s
CPU: Add support for FLOOR,CEIL,ROUND and TRUNC unary operators Pull Request Labeler #17673: Pull request #16083 synchronize by safranowith
13s
13s
CPU: Add support for FLOOR,CEIL,ROUND and TRUNC unary operators Pull Request Labeler #17672: Pull request #16083 synchronize by safranowith
3m 39s
3m 39s
CUDA: Changing the CUDA scheduling strategy to spin Pull Request Labeler #17671: Pull request #16585 synchronize by JTischbein
7m 3s
7m 3s
CUDA: Changing the CUDA scheduling strategy to spin Pull Request Labeler #17670: Pull request #16585 synchronize by JTischbein
59s
59s
Add OpenVINO backend Pull Request Labeler #17669: Pull request #15307 synchronize by wine99
19m 2s
19m 2s
fix(ggml): use safe character conversion in ggml_fopen on Windows Pull Request Labeler #17668: Pull request #16589 opened by sirus20x6
49s
49s
feat(ggml): vectorize row conversion functions Pull Request Labeler #17667: Pull request #16588 opened by sirus20x6
5m 14s
5m 14s
feat(ggml): vectorize row conversion functions Pull Request Labeler #17666: Pull request #16587 opened by sirus20x6
5m 37s
5m 37s
CUDA: Changing the CUDA scheduling strategy to spin Pull Request Labeler #17665: Pull request #16585 opened by JTischbein
5m 46s
5m 46s