Skip to content

Actions: ggerganov/llama.cpp

Actions

Benchmark

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
bench.yml
This workflow was disabled manually.
2,232 workflow runs
2,232 workflow runs
Event

Filter by event

Loading
Status

Filter by status

Loading
Branch
Actor

Filter by actor

Loading
move BLAS to a separate backend Benchmark #2138: Pull request #6210 synchronize by slaren
June 7, 2024 02:16 46m 2s
June 7, 2024 02:16 46m 2s
move BLAS to a separate backend Benchmark #2137: Pull request #6210 synchronize by slaren
June 6, 2024 23:57 46m 49s
June 6, 2024 23:57 46m 49s
check for nans in imatrix and quantize Benchmark #2136: Pull request #7807 opened by slaren
June 6, 2024 20:47 56m 21s
June 6, 2024 20:47 56m 21s
Allow pooled embeddings on any model Benchmark #2135: Pull request #7477 synchronize by iamlemec
June 6, 2024 20:11 43m 55s
June 6, 2024 20:11 43m 55s
imatrix : migrate to gpt_params (#7771) Benchmark #2134: Commit f83351f pushed by ggerganov
June 6, 2024 13:31 2h 5m 26s master
master
June 6, 2024 13:31 2h 5m 26s
Added support for . (any character) token in grammar engine. (#6467) Benchmark #2133: Commit ad675e1 pushed by HanClinto
June 6, 2024 13:08 1h 38m 30s master
master
June 6, 2024 13:08 1h 38m 30s
Added support for . (any character) token in grammar engine. Benchmark #2132: Pull request #6467 synchronize by HanClinto
June 6, 2024 13:02 57m 30s
June 6, 2024 13:02 57m 30s
ggml-qnn: add Qualcomm QNN(Qualcomm Neural Network,aka Qualcomm AI Engine Direct) backend Benchmark #2131: Pull request #6869 synchronize by zhouwg
June 6, 2024 12:24 46m 25s
June 6, 2024 12:24 46m 25s
ggml-qnn: add Qualcomm QNN(Qualcomm Neural Network,aka Qualcomm AI Engine Direct) backend Benchmark #2130: Pull request #6869 synchronize by zhouwg
June 6, 2024 09:12 2h 0m 10s
June 6, 2024 09:12 2h 0m 10s
ggml-qnn: add Qualcomm QNN(Qualcomm Neural Network,aka Qualcomm AI Engine Direct) backend Benchmark #2129: Pull request #6869 synchronize by zhouwg
June 6, 2024 09:12 29s
June 6, 2024 09:12 29s
ggml-qnn: add Qualcomm QNN(Qualcomm Neural Network,aka Qualcomm AI Engine Direct) backend Benchmark #2128: Pull request #6869 synchronize by zhouwg
June 6, 2024 08:50 22m 1s
June 6, 2024 08:50 22m 1s
ggml-qnn: add Qualcomm QNN(Qualcomm Neural Network,aka Qualcomm AI Engine Direct) backend Benchmark #2127: Pull request #6869 synchronize by zhouwg
June 6, 2024 08:49 36s
June 6, 2024 08:49 36s
feat: add changes to handle jina v2 chinese code Benchmark #2126: Pull request #7795 synchronize by JoanFM
June 6, 2024 08:31 1h 54m 58s
June 6, 2024 08:31 1h 54m 58s
WIP: Use DirectStorage with CUDA interop to more efficient load tensors Benchmark #2125: Pull request #7796 opened by mtavenrath
June 6, 2024 08:27 1h 11m 32s
June 6, 2024 08:27 1h 11m 32s
feat: add changes to handle jina v2 chinese code Benchmark #2124: Pull request #7795 synchronize by JoanFM
June 6, 2024 08:20 10m 54s
June 6, 2024 08:20 10m 54s
feat: add changes to handle jina v2 chinese code Benchmark #2123: Pull request #7795 opened by JoanFM
June 6, 2024 08:19 1m 55s
June 6, 2024 08:19 1m 55s
llama : add jina v2 base code (#7596) Benchmark #2122: Commit f5d7b26 pushed by ggerganov
June 6, 2024 07:22 1h 33m 34s master
master
June 6, 2024 07:22 1h 33m 34s
feat: add changes to handle jina v2 base code Benchmark #2121: Pull request #7596 synchronize by ggerganov
June 6, 2024 07:22 46m 19s
June 6, 2024 07:22 46m 19s
ggml-qnn: add Qualcomm QNN(Qualcomm Neural Network,aka Qualcomm AI Engine Direct) backend Benchmark #2120: Pull request #6869 synchronize by zhouwg
June 6, 2024 06:27 46m 21s
June 6, 2024 06:27 46m 21s
Benchmark Benchmark #2119: Scheduled
June 6, 2024 02:19 47m 41s master
master
June 6, 2024 02:19 47m 41s
move BLAS to a separate backend Benchmark #2118: Pull request #6210 synchronize by slaren
June 6, 2024 01:14 46m 23s
June 6, 2024 01:14 46m 23s
move BLAS to a separate backend Benchmark #2117: Pull request #6210 synchronize by slaren
June 6, 2024 00:18 46m 16s
June 6, 2024 00:18 46m 16s
Added support for . (any character) token in grammar engine. Benchmark #2116: Pull request #6467 synchronize by HanClinto
June 5, 2024 22:58 48m 19s
June 5, 2024 22:58 48m 19s
Added support for . (any character) token in grammar engine. Benchmark #2115: Pull request #6467 synchronize by HanClinto
June 5, 2024 22:43 15m 30s
June 5, 2024 22:43 15m 30s
imatrix : migrate to gpt_params Benchmark #2114: Pull request #7771 synchronize by ggerganov
June 5, 2024 19:13 1h 5m 14s
June 5, 2024 19:13 1h 5m 14s