Skip to content

Actions: ggml-org/llama.cpp

Actions

Pull Request Labeler

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
labeler.yml
14,480 workflow runs
14,480 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

vulkan: Add ACC_TYPE_VEC2 implementation Pull Request Labeler #17249: Pull request #16203 synchronize by SavicStefan
12s
12s
server / ranking : add sorting and management of top_n Pull Request Labeler #17248: Pull request #16403 synchronize by YannFollet
16s
16s
model: EmbeddingGemma Adding Support for SentenceTransformers Dense Modules Pull Request Labeler #17247: Pull request #16367 synchronize by sfallah
1m 20s
1m 20s
model: EmbeddingGemma Adding Support for SentenceTransformers Dense Modules Pull Request Labeler #17246: Pull request #16367 synchronize by sfallah
3m 9s
3m 9s
refactor: centralize CoT parsing in backend for streaming mode Pull Request Labeler #17245: Pull request #16394 synchronize by ServeurpersoCom
12s
12s
Stub out bc6h support Pull Request Labeler #17244: Pull request #16419 opened by monocasa
12s
12s
vulkan: use a more appropriate amount of threads when generating shaders Pull Request Labeler #17243: Pull request #16418 synchronize by netrunnereve
12s
12s
vulkan : incremental shader builds Pull Request Labeler #17242: Pull request #16341 synchronize by Acly
12s
12s
vulkan: use a more appropriate amount of threads when generating shaders Pull Request Labeler #17241: Pull request #16418 opened by netrunnereve
15s
15s
quantize: add option to automatically choose optimal quant types to reach a bpw target at lowest error Pull Request Labeler #17240: Pull request #15550 synchronize by EAddario
11s
11s
imatrix: calculate activation-based statistics for new format (GGUF) imatrices Pull Request Labeler #17239: Pull request #14891 synchronize by EAddario
11s
11s
ggml webgpu: actually add softmax, fix rms_norm offset Pull Request Labeler #17238: Pull request #16400 synchronize by reeselevine
3m 21s
3m 21s
Model: Qwen3 Next Pull Request Labeler #17237: Pull request #16095 synchronize by pwilkin
3m 21s
3m 21s
refactor: centralize CoT parsing in backend for streaming mode Pull Request Labeler #17236: Pull request #16394 synchronize by ServeurpersoCom
45m 13s
45m 13s
server : host-memory prompt caching Pull Request Labeler #17235: Pull request #16391 synchronize by ggerganov
6m 2s
6m 2s
ci : refactor sdk caching to minimize storage Pull Request Labeler #17234: Pull request #16414 opened by CISC
3m 53s
3m 53s
implement context checkpointing for hybrid and recurrent models Pull Request Labeler #17233: Pull request #16382 synchronize by ggerganov
10s
10s
Magistral Pull Request Labeler #17232: Pull request #16413 opened by ServeurpersoCom
2m 56s
2m 56s
Model: Granite docling + Idefics3 preprocessing (SmolVLM) Pull Request Labeler #17231: Pull request #16206 synchronize by gabe-l-hart
14s
14s
Model: Granite docling + Idefics3 preprocessing (SmolVLM) Pull Request Labeler #17230: Pull request #16206 synchronize by gabe-l-hart
13s
13s
refactor: centralize CoT parsing in backend for streaming mode Pull Request Labeler #17229: Pull request #16394 synchronize by ServeurpersoCom
22s
22s
metal : fix loop bound in ggml_mem_ranges Pull Request Labeler #17228: Pull request #16412 opened by ggerganov
15s
15s
refactor: centralize CoT parsing in backend for streaming mode Pull Request Labeler #17227: Pull request #16394 synchronize by ServeurpersoCom
12s
12s
refactor: centralize CoT parsing in backend for streaming mode Pull Request Labeler #17226: Pull request #16394 synchronize by ServeurpersoCom
13s
13s
refactor: centralize CoT parsing in backend for streaming mode Pull Request Labeler #17225: Pull request #16394 synchronize by ServeurpersoCom
12m 21s
12m 21s
ProTip! You can narrow down the results and go further in time using created:<2025-10-03 or the other filters available.