Skip to content

Actions: ggerganov/llama.cpp

Actions

Benchmark

Actions

Loading...

Show workflow options

Create status badge

bench.yml
2,189 workflow runs
2,189 workflow runs
Event

Filter by event
Status

Filter by status
Branch
Actor

Filter by actor
ggml-qnn: add Qualcomm QNN(Qualcomm Neural Network,aka Qualcomm AI Engine Direct) backend Benchmark #2195: Pull request #6869 synchronize by zhouwg
June 9, 2024 15:50 Queued
June 9, 2024 15:50 Queued
ggml-qnn: add Qualcomm QNN(Qualcomm Neural Network,aka Qualcomm AI Engine Direct) backend Benchmark #2194: Pull request #6869 synchronize by zhouwg
June 9, 2024 15:49 22s
June 9, 2024 15:49 22s
ggml-qnn: add Qualcomm QNN(Qualcomm Neural Network,aka Qualcomm AI Engine Direct) backend Benchmark #2193: Pull request #6869 synchronize by zhouwg
June 9, 2024 15:49 28s
June 9, 2024 15:49 28s
ggml-qnn: add Qualcomm QNN(Qualcomm Neural Network,aka Qualcomm AI Engine Direct) backend Benchmark #2192: Pull request #6869 synchronize by zhouwg
June 9, 2024 15:36 13m 12s
June 9, 2024 15:36 13m 12s
ggml-qnn: add Qualcomm QNN(Qualcomm Neural Network,aka Qualcomm AI Engine Direct) backend Benchmark #2191: Pull request #6869 synchronize by zhouwg
June 9, 2024 15:36 20s
June 9, 2024 15:36 20s
ggml-qnn: add Qualcomm QNN(Qualcomm Neural Network,aka Qualcomm AI Engine Direct) backend Benchmark #2190: Pull request #6869 synchronize by zhouwg
June 9, 2024 15:35 29s
June 9, 2024 15:35 29s
ggml-qnn: add Qualcomm QNN(Qualcomm Neural Network,aka Qualcomm AI Engine Direct) backend Benchmark #2189: Pull request #6869 synchronize by zhouwg
June 9, 2024 15:28 6m 51s
June 9, 2024 15:28 6m 51s
ggml-qnn: add Qualcomm QNN(Qualcomm Neural Network,aka Qualcomm AI Engine Direct) backend Benchmark #2188: Pull request #6869 synchronize by zhouwg
June 9, 2024 15:28 29s
June 9, 2024 15:28 29s
ggml-qnn: add Qualcomm QNN(Qualcomm Neural Network,aka Qualcomm AI Engine Direct) backend Benchmark #2187: Pull request #6869 synchronize by zhouwg
June 9, 2024 15:28 28s
June 9, 2024 15:28 28s
ggml-qnn: add Qualcomm QNN(Qualcomm Neural Network,aka Qualcomm AI Engine Direct) backend Benchmark #2186: Pull request #6869 synchronize by zhouwg
June 9, 2024 15:27 20s
June 9, 2024 15:27 20s
ggml-qnn: add Qualcomm QNN(Qualcomm Neural Network,aka Qualcomm AI Engine Direct) backend Benchmark #2185: Pull request #6869 synchronize by zhouwg
June 9, 2024 15:27 31s
June 9, 2024 15:27 31s
llama_supports_rpc() function Benchmark #2184: Pull request #7647 synchronize by martindevans
June 9, 2024 15:22 Queued
June 9, 2024 15:22 Queued
llama_supports_rpc() function Benchmark #2183: Pull request #7647 synchronize by martindevans
June 9, 2024 15:21 49s
June 9, 2024 15:21 49s
llama_supports_rpc() function Benchmark #2182: Pull request #7647 synchronize by martindevans
June 9, 2024 15:17 4m 24s
June 9, 2024 15:17 4m 24s
More checks before assuming FIM tokens Benchmark #2181: Pull request #7644 synchronize by CISC
June 9, 2024 09:58 Queued
June 9, 2024 09:58 Queued
ggml-qnn: add Qualcomm QNN(Qualcomm Neural Network,aka Qualcomm AI Engine Direct) backend Benchmark #2180: Pull request #6869 synchronize by zhouwg
June 9, 2024 08:48 6h 39m 13s
June 9, 2024 08:48 6h 39m 13s
[WIP] agent example (w/ sandboxable Tools!) & improved OAI compatibility layer (in Python) Benchmark #2179: Pull request #6389 synchronize by ochafik
June 9, 2024 08:27 Queued
June 9, 2024 08:27 Queued
CUDA: use tensor cores for MMQ Benchmark #2178: Pull request #7676 synchronize by JohannesGaessler
June 9, 2024 07:43 Queued
June 9, 2024 07:43 Queued
CUDA: revise q8_1 data layout for mul_mat_q (#7824) Benchmark #2177: Commit 42b53d1 pushed by JohannesGaessler
June 9, 2024 07:42 Queued master
master
June 9, 2024 07:42 Queued
CUDA: revise q8_1 data layout for mul_mat_q Benchmark #2176: Pull request #7824 synchronize by JohannesGaessler
June 9, 2024 06:21 Queued
June 9, 2024 06:21 Queued
Benchmark Benchmark #2175: Scheduled
June 9, 2024 02:23 Queued master
master
June 9, 2024 02:23 Queued
ggml-qnn: add Qualcomm QNN(Qualcomm Neural Network,aka Qualcomm AI Engine Direct) backend Benchmark #2174: Pull request #6869 synchronize by zhouwg
June 9, 2024 01:06 7h 41m 18s
June 9, 2024 01:06 7h 41m 18s
ggml-qnn: add Qualcomm QNN(Qualcomm Neural Network,aka Qualcomm AI Engine Direct) backend Benchmark #2173: Pull request #6869 synchronize by zhouwg
June 9, 2024 01:06 16s
June 9, 2024 01:06 16s
ggml-qnn: add Qualcomm QNN(Qualcomm Neural Network,aka Qualcomm AI Engine Direct) backend Benchmark #2172: Pull request #6869 synchronize by zhouwg
June 9, 2024 01:06 32s
June 9, 2024 01:06 32s
ggml-qnn: add Qualcomm QNN(Qualcomm Neural Network,aka Qualcomm AI Engine Direct) backend Benchmark #2171: Pull request #6869 synchronize by zhouwg
June 9, 2024 01:04 2m 26s
June 9, 2024 01:04 2m 26s