Skip to content

Actions: ggml-org/llama.cpp

Actions

Pull Request Labeler

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
labeler.yml
14,264 workflow runs
14,264 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

llama-model: fix insonsistent ctxs <-> bufs order Pull Request Labeler #17645: Pull request #16581 opened by JohannesGaessler
1m 35s
1m 35s
Add experimental ggml-hexagon backend for the Hexagon NPU Pull Request Labeler #17644: Pull request #16547 synchronize by max-krasnyansky
14m 35s
14m 35s
Implement and use cuda graph plans Pull Request Labeler #17643: Pull request #16548 synchronize by wishstudio
30m 22s
30m 22s
Model: Qwen3 Next Pull Request Labeler #17642: Pull request #16095 synchronize by pwilkin
11s
11s
CUDA + openCL: fix bug in accessing rms_norm->src while doing fusion Pull Request Labeler #17641: Pull request #16577 opened by am17an
2m 31s
2m 31s
vulkan: Add State Space Model (SSM) Operations Support Pull Request Labeler #17640: Pull request #16463 synchronize by giuseppe
13m 20s
13m 20s
vulkan: Add State Space Model (SSM) Operations Support Pull Request Labeler #17639: Pull request #16463 synchronize by giuseppe
19s
19s
vulkan: Add ACC_TYPE_VEC2 implementation Pull Request Labeler #17638: Pull request #16203 synchronize by SavicStefan
4m 9s
4m 9s
metal : avoid using Metal's gpuAddress property Pull Request Labeler #17637: Pull request #16576 synchronize by ggerganov
5m 47s
5m 47s
metal : avoid using Metal's gpuAddress property Pull Request Labeler #17636: Pull request #16576 opened by ggerganov
9m 0s
9m 0s
Add CONV_TRANSPOSE_2D for Metal Pull Request Labeler #17635: Pull request #16542 synchronize by iliailmer
4m 22s
4m 22s
ggml-cpu: build fails with -Werror=discarded-qualifiers Pull Request Labeler #17634: Pull request #16573 synchronize by otegami
23m 40s
23m 40s
CUDA: add fp kernel for larger batch size MoE Pull Request Labeler #17633: Pull request #16512 synchronize by am17an
11s
11s
CUDA: use fastdiv + ggml_cuda_mad for mmvf Pull Request Labeler #17632: Pull request #16557 synchronize by am17an
10s
10s
mtmd: Add JinaCLIP v2 vision projector + GGUF support for jina-bert-v3 (merged-LoRA or adapter) Pull Request Labeler #17631: Pull request #16574 opened by pockers21
14s
14s
ggml-cpu: build fails with -Werror=discarded-qualifiers Pull Request Labeler #17630: Pull request #16573 opened by otegami
12s
12s
Add OpenVINO backend Pull Request Labeler #17629: Pull request #15307 synchronize by wine99
3m 57s
3m 57s
CUDA: use fastdiv + ggml_cuda_mad for mmvf Pull Request Labeler #17628: Pull request #16557 synchronize by am17an
10s
10s
Fix: Avoiding SQL string concatenation: untrusted input concatenated with raw SQL query can result in SQL Injection. In order to execute raw query safely, prepared statement should be used. SQLAlchemy provides TextualSQL to easily used prepared statement with named parameters. For complex SQL composition, use SQL Expression Language or Schema Definition Language. In most cases, SQLAlchemy ORM will be a better option. in scripts/compare-llama-bench.py Pull Request Labeler #17627: Pull request #16572 opened by orbisai-sec
11s
11s
Fix: Detected possible formatted SQL query. Use parameterized queries instead. in scripts/compare-llama-bench.py Pull Request Labeler #17626: Pull request #16571 opened by orbisai-sec
11s
11s
CUDA: use fastdiv + ggml_cuda_mad for mmvf Pull Request Labeler #17625: Pull request #16557 synchronize by am17an
11s
11s
CUDA: use fastdiv + ggml_cuda_mad for mmvf Pull Request Labeler #17624: Pull request #16557 synchronize by am17an
12s
12s
CUDA: use fastdiv + ggml_cuda_mad for mmvf Pull Request Labeler #17623: Pull request #16557 synchronize by am17an
14s
14s
CUDA: use fastdiv + ggml_cuda_mad for mmvf Pull Request Labeler #17622: Pull request #16557 synchronize by am17an
30s
30s
CUDA: add fp kernel for larger batch size MoE Pull Request Labeler #17621: Pull request #16512 synchronize by am17an
3m 16s
3m 16s