Skip to content

Actions: ggerganov/llama.cpp

Actions

Benchmark

Actions

Loading...

Show workflow options

Create status badge

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

Filter by event
Status

Filter by status
Branch
Actor

Filter by actor
AVX IQ Quants Benchmark #2238: Pull request #7845 synchronize by netrunnereve
June 12, 2024 03:27 1d 2h 8m 24s
June 12, 2024 03:27 1d 2h 8m 24s
Benchmark Benchmark #2237: Scheduled
June 12, 2024 02:21 1d 3h 14m 23s master
master
June 12, 2024 02:21 1d 3h 14m 23s
Add PaliGemma Support Benchmark #2236: Pull request #7553 synchronize by abetlen
June 12, 2024 01:12 1d 4h 22m 49s
June 12, 2024 01:12 1d 4h 22m 49s
move BLAS to a separate backend Benchmark #2235: Pull request #6210 synchronize by slaren
June 11, 2024 21:35 1d 7h 59m 56s
June 11, 2024 21:35 1d 7h 59m 56s
AVX IQ Quants Benchmark #2234: Pull request #7845 synchronize by netrunnereve
June 11, 2024 19:55 7h 31m 43s
June 11, 2024 19:55 7h 31m 43s
AVX IQ Quants Benchmark #2233: Pull request #7845 synchronize by netrunnereve
June 11, 2024 19:55 27s
June 11, 2024 19:55 27s
server : restore numeric prompts Benchmark #2232: Pull request #7883 opened by ggerganov
June 11, 2024 16:48 1d 12h 46m 57s
June 11, 2024 16:48 1d 12h 46m 57s
ggml-qnn: add Qualcomm QNN(Qualcomm Neural Network,aka Qualcomm AI Engine Direct) backend Benchmark #2231: Pull request #6869 synchronize by zhouwg
June 11, 2024 15:05 1d 14h 30m 23s
June 11, 2024 15:05 1d 14h 30m 23s
ggml-qnn: add Qualcomm QNN(Qualcomm Neural Network,aka Qualcomm AI Engine Direct) backend Benchmark #2230: Pull request #6869 synchronize by zhouwg
June 11, 2024 15:04 59s
June 11, 2024 15:04 59s
ggml-qnn: add Qualcomm QNN(Qualcomm Neural Network,aka Qualcomm AI Engine Direct) backend Benchmark #2229: Pull request #6869 synchronize by zhouwg
June 11, 2024 09:31 5h 33m 19s
June 11, 2024 09:31 5h 33m 19s
ggml-qnn: add Qualcomm QNN(Qualcomm Neural Network,aka Qualcomm AI Engine Direct) backend Benchmark #2228: Pull request #6869 synchronize by zhouwg
June 11, 2024 09:30 1m 3s
June 11, 2024 09:30 1m 3s
add chatglm3-6b and glm-4-9b-chat model support Benchmark #2227: Pull request #6999 synchronize by mnlife
June 11, 2024 07:47 1d 7h 6m 44s
June 11, 2024 07:47 1d 7h 6m 44s
add chatglm3-6b and glm-4-9b-chat model support Benchmark #2226: Pull request #6999 synchronize by mnlife
June 11, 2024 06:34 1h 13m 7s
June 11, 2024 06:34 1h 13m 7s
ggml-qnn: add Qualcomm QNN(Qualcomm Neural Network,aka Qualcomm AI Engine Direct) backend Benchmark #2225: Pull request #6869 synchronize by zhouwg
June 11, 2024 04:21 5h 9m 3s
June 11, 2024 04:21 5h 9m 3s
ggml-qnn: add Qualcomm QNN(Qualcomm Neural Network,aka Qualcomm AI Engine Direct) backend Benchmark #2224: Pull request #6869 synchronize by zhouwg
June 11, 2024 04:20 27s
June 11, 2024 04:20 27s
ggml-qnn: add Qualcomm QNN(Qualcomm Neural Network,aka Qualcomm AI Engine Direct) backend Benchmark #2223: Pull request #6869 synchronize by zhouwg
June 11, 2024 04:20 27s
June 11, 2024 04:20 27s
ggml-qnn: add Qualcomm QNN(Qualcomm Neural Network,aka Qualcomm AI Engine Direct) backend Benchmark #2222: Pull request #6869 synchronize by zhouwg
June 11, 2024 03:54 26m 9s
June 11, 2024 03:54 26m 9s
Benchmark Benchmark #2221: Scheduled
June 11, 2024 02:21 1d 3h 14m 31s master
master
June 11, 2024 02:21 1d 3h 14m 31s
add chatglm3-6b and glm-4-9b-chat model support Benchmark #2220: Pull request #6999 synchronize by mnlife
June 11, 2024 01:59 4h 34m 16s
June 11, 2024 01:59 4h 34m 16s
update: support Qwen2-57B-A14B Benchmark #2219: Pull request #7835 synchronize by legraphista
June 10, 2024 17:51 1d 11h 44m 18s
June 10, 2024 17:51 1d 11h 44m 18s
WIP: Use DirectStorage with CUDA interop to more efficient load tensors Benchmark #2218: Pull request #7796 reopened by mtavenrath
June 10, 2024 16:39 1d 12h 56m 20s
June 10, 2024 16:39 1d 12h 56m 20s
tests : add non-cont unary tests Benchmark #2217: Pull request #7857 opened by ggerganov
June 10, 2024 14:13 1d 0h 39m 59s
June 10, 2024 14:13 1d 0h 39m 59s
ggml : improve ggml_is_contiguous logic Benchmark #2216: Pull request #7856 opened by ggerganov
June 10, 2024 14:10 1d 0h 43m 42s
June 10, 2024 14:10 1d 0h 43m 42s
ggml-qnn: add Qualcomm QNN(Qualcomm Neural Network,aka Qualcomm AI Engine Direct) backend Benchmark #2215: Pull request #6869 synchronize by zhouwg
June 10, 2024 12:07 15h 46m 46s
June 10, 2024 12:07 15h 46m 46s
ggml-qnn: add Qualcomm QNN(Qualcomm Neural Network,aka Qualcomm AI Engine Direct) backend Benchmark #2214: Pull request #6869 synchronize by zhouwg
June 10, 2024 12:07 17s
June 10, 2024 12:07 17s