Skip to content

Actions: ggerganov/llama.cpp

Benchmark

Actions

Loading...

Show workflow options

Create status badge

2,073 workflow runs
2,073 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 #2079: Pull request #6869 synchronize by zhouwg
June 5, 2024 00:56 Queued
June 5, 2024 00:56 Queued
ggml-qnn: add Qualcomm QNN(Qualcomm Neural Network,aka Qualcomm AI Engine Direct) backend
Benchmark #2078: Pull request #6869 synchronize by zhouwg
June 5, 2024 00:56 44s
June 5, 2024 00:56 44s
ggml-qnn: add Qualcomm QNN(Qualcomm Neural Network,aka Qualcomm AI Engine Direct) backend
Benchmark #2077: Pull request #6869 synchronize by zhouwg
June 5, 2024 00:50 5m 49s
June 5, 2024 00:50 5m 49s
move BLAS to a separate backend
Benchmark #2076: Pull request #6210 synchronize by slaren
June 4, 2024 23:16 1h 32m 55s
June 4, 2024 23:16 1h 32m 55s
Allow number of nodes in CUDA graph to change (#7738)
Benchmark #2075: Commit b90dc56 pushed by slaren
June 4, 2024 20:06 3h 56m 44s master
June 4, 2024 20:06 3h 56m 44s
move BLAS to a separate backend
Benchmark #2074: Pull request #6210 synchronize by slaren
June 4, 2024 18:51 4h 25m 34s
June 4, 2024 18:51 4h 25m 34s
common : refactor cli arg parsing (#7675)
Benchmark #2073: Commit 1442677 pushed by ggerganov
June 4, 2024 18:23 4h 24m 43s master
June 4, 2024 18:23 4h 24m 43s
ggml : remove OpenCL (#7735)
Benchmark #2072: Commit 554c247 pushed by ggerganov
June 4, 2024 18:23 3h 39m 13s master
June 4, 2024 18:23 3h 39m 13s
llama : remove beam search (#7736)
Benchmark #2071: Commit 0cd6bd3 pushed by ggerganov
June 4, 2024 18:23 2h 53m 35s master
June 4, 2024 18:23 2h 53m 35s
move BLAS to a separate backend
Benchmark #2070: Pull request #6210 synchronize by slaren
June 4, 2024 18:13 37m 34s
June 4, 2024 18:13 37m 34s
Fix per token atrributes bits
Benchmark #2069: Pull request #7749 opened by jaime-m-p
June 4, 2024 17:08 3h 21m 55s
June 4, 2024 17:08 3h 21m 55s
Allow pooled embeddings on any model
Benchmark #2068: Pull request #7477 synchronize by iamlemec
June 4, 2024 16:17 3h 27m 30s
June 4, 2024 16:17 3h 27m 30s
feat: add changes to handle jina v2 base code
Benchmark #2067: Pull request #7596 synchronize by JoanFM
June 4, 2024 15:08 3h 50m 6s
June 4, 2024 15:08 3h 50m 6s
feat: add changes to handle jina v2 base code
Benchmark #2066: Pull request #7596 synchronize by JoanFM
June 4, 2024 15:02 6m 38s
June 4, 2024 15:02 6m 38s
Catch exceptions correctly in server.cpp
Benchmark #2065: Pull request #7642 synchronize by 0wwafa
June 4, 2024 14:48 3h 23m 51s
June 4, 2024 14:48 3h 23m 51s
server : add /v1/completion endpoint
Benchmark #2064: Pull request #7741 opened by ggerganov
June 4, 2024 12:58 4h 27m 56s
June 4, 2024 12:58 4h 27m 56s
[CANN] Add Ascend NPU backend
Benchmark #2063: Pull request #6035 synchronize by wangshuai09
June 4, 2024 12:35 4h 4m 39s
June 4, 2024 12:35 4h 4m 39s
Allow number of nodes in CUDA graph to change
Benchmark #2062: Pull request #7738 opened by agray3
June 4, 2024 12:32 3h 25m 58s
June 4, 2024 12:32 3h 25m 58s
common : refactor cli arg parsing
Benchmark #2061: Pull request #7675 synchronize by ggerganov
June 4, 2024 11:54 3h 14m 50s
June 4, 2024 11:54 3h 14m 50s
ggml-qnn: add Qualcomm QNN(Qualcomm Neural Network,aka Qualcomm AI Engine Direct) backend
Benchmark #2060: Pull request #6869 synchronize by zhouwg
June 4, 2024 11:45 2h 38m 38s
June 4, 2024 11:45 2h 38m 38s
llama : remove beam search
Benchmark #2059: Pull request #7736 opened by ggerganov
June 4, 2024 11:33 2h 4m 39s
June 4, 2024 11:33 2h 4m 39s
ggml : remove OpenCL
Benchmark #2058: Pull request #7735 opened by ggerganov
June 4, 2024 11:12 1h 38m 50s
June 4, 2024 11:12 1h 38m 50s
common : refactor cli arg parsing
Benchmark #2057: Pull request #7675 synchronize by ggerganov
June 4, 2024 10:08 1h 46m 28s
June 4, 2024 10:08 1h 46m 28s
common : refactor cli arg parsing
Benchmark #2056: Pull request #7675 synchronize by ggerganov
June 4, 2024 09:42 26m 13s
June 4, 2024 09:42 26m 13s
[SYCL] remove global variables
Benchmark #2055: Pull request #7710 synchronize by airMeng
June 4, 2024 08:48 3h 14m 1s
June 4, 2024 08:48 3h 14m 1s