Skip to content

Actions: ggml-org/llama.cpp

Actions

Pull Request Labeler

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
labeler.yml
17,750 workflow runs
17,750 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

Add EXAONE MoE implementations Pull Request Labeler #22981: Pull request #18543 synchronize by nuxlear
Queued
Queued
HIP: add fattn-mma-f16 for RDNA4 Pull Request Labeler #22980: Pull request #18481 synchronize by zhang-hui-yulo
17s
17s
debug : include LLAMA_POOLING_TYPE_UNSPECIFIED in pooling check Pull Request Labeler #22979: Pull request #18692 opened by danbev
19s
19s
model-conversion : add warn about transformers mismatch Pull Request Labeler #22978: Pull request #18691 opened by danbev
15s
15s
ggml-cuda: extend concat support for more types Pull Request Labeler #22977: Pull request #18690 opened by Lourdle
1m 0s
1m 0s
model-conversion : remove -st targets for converted model Pull Request Labeler #22976: Pull request #18689 opened by danbev
18m 0s
18m 0s
vulkan: fix push constant size for quantize_q8_1 Pull Request Labeler #22975: Pull request #18687 synchronize by jeffbolznv
28s
28s
vulkan: fix push constant size for quantize_q8_1 Pull Request Labeler #22974: Pull request #18687 synchronize by jeffbolznv
3m 12s
3m 12s
vulkan: fix push constant size for quantize_q8_1 Pull Request Labeler #22973: Pull request #18687 opened by jeffbolznv
11s
11s
Add EXAONE MoE implementations Pull Request Labeler #22972: Pull request #18543 synchronize by nuxlear
22s
22s
full modern bert support Pull Request Labeler #22971: Pull request #18330 synchronize by ryan-mangeno
10s
10s
ggml-webgpu: Fix GGML_MEM_ALIGN to 8 for emscripten. Pull Request Labeler #22970: Pull request #18628 synchronize by yomaytk
12s
12s
ggml-webgpu: Fix GGML_MEM_ALIGN to 8 for emscripten. Pull Request Labeler #22969: Pull request #18628 synchronize by yomaytk
12s
12s
ggml webgpu: initial flashattention implementation Pull Request Labeler #22968: Pull request #18610 synchronize by reeselevine
1h 28m 57s
1h 28m 57s
implement adaptive-p sampler Pull Request Labeler #22967: Pull request #17927 synchronize by ddh0
1h 0m 25s
1h 0m 25s
model: try to improve Qwen3 Next Pull Request Labeler #22966: Pull request #18683 opened by ngxson
1h 1m 55s
1h 1m 55s
opencl: add fill op Pull Request Labeler #22965: Pull request #18682 opened by shaofeiqi
44m 32s
44m 32s
Autoparser - complete refactoring of parser architecture Pull Request Labeler #22964: Pull request #18675 synchronize by pwilkin
19m 16s
19m 16s
implement adaptive-p sampler Pull Request Labeler #22963: Pull request #17927 synchronize by ddh0
15m 40s
15m 40s
Add support for IQuest-Loop-Instruct loop attention mechanism Pull Request Labeler #22962: Pull request #18680 opened by tbraun96
42m 9s
42m 9s
llama-fit-params: free memory target per device Pull Request Labeler #22961: Pull request #18679 opened by JohannesGaessler
33m 28s
33m 28s
quantize: add option to automatically choose optimal quant types to reach a file/bpw target size at lowest error Pull Request Labeler #22960: Pull request #15550 synchronize by EAddario
27m 56s
27m 56s
imatrix: calculate activation-based statistics for new format (GGUF) imatrices Pull Request Labeler #22959: Pull request #14891 synchronize by EAddario
14m 37s
14m 37s
Autoparser - complete refactoring of parser architecture Pull Request Labeler #22958: Pull request #18675 synchronize by pwilkin
12m 27s
12m 27s
Add EXAONE MoE implementations Pull Request Labeler #22957: Pull request #18543 synchronize by nuxlear
27m 37s
27m 37s