Skip to content

Actions: ggml-org/llama.cpp

Actions

All workflows

Actions

Loading...
Loading

Showing runs from all workflows
51,367 workflow run results
51,367 workflow run results

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

webui: prettify styling Pull Request Labeler #14583: Pull request #15201 opened by olegshulyakov
11s
11s
fix: llama_memory_seq_rm(mem, -1, ...) Server #17343: Pull request #15200 opened by leok7v
52m 5s leok7v:master
leok7v:master
52m 5s
fix: llama_memory_seq_rm(mem, -1, ...) CI #25921: Pull request #15200 opened by leok7v
2h 16m 28s leok7v:master
leok7v:master
2h 16m 28s
fix: llama_memory_seq_rm(mem, -1, ...) EditorConfig Checker #29109: Pull request #15200 opened by leok7v
6m 8s leok7v:master
leok7v:master
6m 8s
fix: llama_memory_seq_rm(mem, -1, ...) Pull Request Labeler #14582: Pull request #15200 opened by leok7v
13s
13s
gpt-oss: implement harmony parsing Server #17342: Pull request #15181 synchronize by aldehir
12m 17s aldehir:feature/harmony-parser
aldehir:feature/harmony-parser
12m 17s
gpt-oss: implement harmony parsing EditorConfig Checker #29108: Pull request #15181 synchronize by aldehir
23s aldehir:feature/harmony-parser
aldehir:feature/harmony-parser
23s
gpt-oss: implement harmony parsing CI #25920: Pull request #15181 synchronize by aldehir
1h 4m 39s aldehir:feature/harmony-parser
aldehir:feature/harmony-parser
1h 4m 39s
gpt-oss: implement harmony parsing Pull Request Labeler #14581: Pull request #15181 synchronize by aldehir
9s
9s
Fix GPT-OSS Harmony format end token handling crash Pull Request Labeler #14580: Pull request #15195 synchronize by trvon
12s
12s
cuda: refactored ssm_scan and use CUB (#13291) CI #25918: Commit 79c1160 pushed by JohannesGaessler
1h 5m 0s master
master
1h 5m 0s
cuda: refactored ssm_scan and use CUB (#13291) Server #17340: Commit 79c1160 pushed by JohannesGaessler
12m 6s master
master
12m 6s
cuda: refactored ssm_scan and use CUB (#13291) Release #639: Commit 79c1160 pushed by JohannesGaessler
13m 33s master
master
13m 33s
cuda: refactored ssm_scan and use CUB (#13291) EditorConfig Checker #29106: Commit 79c1160 pushed by JohannesGaessler
19s master
master
19s
Fix GPT-OSS Harmony format end token handling crash Pull Request Labeler #14579: Pull request #15195 synchronize by trvon
8s
8s
Fix GPT-OSS Harmony format end token handling crash Pull Request Labeler #14578: Pull request #15195 opened by trvon
10s
10s
imatrix: calculate activation-based statistics for new format (GGUF) imatrices CI #25915: Pull request #14891 synchronize by EAddario
1h 3m 30s EAddario:imatrix
EAddario:imatrix
1h 3m 30s
imatrix: calculate activation-based statistics for new format (GGUF) imatrices Server #17337: Pull request #14891 synchronize by EAddario
12m 19s EAddario:imatrix
EAddario:imatrix
12m 19s
imatrix: calculate activation-based statistics for new format (GGUF) imatrices EditorConfig Checker #29103: Pull request #14891 synchronize by EAddario
20s EAddario:imatrix
EAddario:imatrix
20s
imatrix: calculate activation-based statistics for new format (GGUF) imatrices Pull Request Labeler #14577: Pull request #14891 synchronize by EAddario
10s
10s
CUDA: add attention sinks for tile and wmma (#15178) CI #25914: Commit 34c9d76 pushed by am17an
1h 14m 9s master
master
1h 14m 9s
CUDA: add attention sinks for tile and wmma (#15178) EditorConfig Checker #29102: Commit 34c9d76 pushed by am17an
18s master
master
18s
CUDA: add attention sinks for tile and wmma (#15178) Release #638: Commit 34c9d76 pushed by am17an
14m 15s master
master
14m 15s
CUDA: add attention sinks for tile and wmma (#15178) Server #17336: Commit 34c9d76 pushed by am17an
17m 0s master
master
17m 0s
CUDA: add attention sinks for tile and wmma EditorConfig Checker #29101: Pull request #15178 synchronize by am17an
19s am17an:cuda_fattn_tile_wmma
am17an:cuda_fattn_tile_wmma
19s