Skip to content

Actions: ggml-org/whisper.cpp

Actions

All workflows

Actions

Loading...
Loading

Showing runs from all workflows
150 workflow run results
150 workflow run results

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

whisper : zero-out the KV cache upon clear (#2445) Publish Docker image #848: Commit 847f94f pushed by ggerganov
2h 38m 36s master
master
2h 38m 36s
whisper : zero-out the KV cache upon clear (#2445) CI #3105: Commit 847f94f pushed by ggerganov
3h 17m 49s master
master
3h 17m 49s
sync : ggml + llama.cpp Publish Docker image #847: Pull request #2455 synchronize by ggerganov
1h 56m 48s sync
sync
1h 56m 48s
sync : ggml + llama.cpp CI #3104: Pull request #2455 synchronize by ggerganov
2h 52m 23s sync
sync
2h 52m 23s
whisper : zero-out the KV cache upon clear (#2445) CI #3103: Commit 47de411 pushed by ggerganov
2h 49m 27s sync
sync
2h 49m 27s
sync : ggml + llama.cpp Publish Docker image #846: Pull request #2455 synchronize by ggerganov
1h 13m 15s sync
sync
1h 13m 15s
sync : ggml + llama.cpp CI #3102: Pull request #2455 synchronize by ggerganov
2h 24m 31s sync
sync
2h 24m 31s
objc : fix build CI #3101: Commit 0c0247e pushed by ggerganov
2h 10m 36s sync
sync
2h 10m 36s
sync : ggml + llama.cpp CI #3100: Pull request #2455 opened by ggerganov
1h 27m 51s sync
sync
1h 27m 51s
sync : ggml + llama.cpp Publish Docker image #845: Pull request #2455 opened by ggerganov
23m 10s sync
sync
23m 10s
metal : zero-init buffer contexts (#0) CI #3099: Commit 7a2784e pushed by ggerganov
1h 30m 58s sync
sync
1h 30m 58s
ggml-backend : include <cstring> (#0) CI #3098: Commit 68473b4 pushed by ggerganov
1h 22m 21s sync
sync
1h 22m 21s
whisper : adapt to latest ggml (skip) (#0) CI #3097: Commit f287437 pushed by ggerganov
1h 33m 33s sync
sync
1h 33m 33s
whisper : fix excessive memory usage (#2443) Publish Docker image #844: Commit f62a546 pushed by ggerganov
2m 8s master
master
2m 8s
whisper : fix excessive memory usage (#2443) CI #3096: Commit f62a546 pushed by ggerganov
1h 32m 17s master
master
1h 32m 17s
Retry allocation with fallback flags CI #3095: Pull request #2451 opened by SRHMorris
2h 18m 26s SRHMorris:retry-vulkan-mem-alloc
SRHMorris:retry-vulkan-mem-alloc
2h 18m 26s
Retry allocation with fallback flags Publish Docker image #843: Pull request #2451 opened by SRHMorris
11m 58s SRHMorris:retry-vulkan-mem-alloc
SRHMorris:retry-vulkan-mem-alloc
11m 58s
examples : update dr_wav.h to newer version (#2449) Publish Docker image #842: Commit 2944cb7 pushed by ggerganov
1h 11m 50s master
master
1h 11m 50s
examples : update dr_wav.h to newer version (#2449) CI #3094: Commit 2944cb7 pushed by ggerganov
1h 40m 17s master
master
1h 40m 17s
whisper : fix excessive memory usage Publish Docker image #841: Pull request #2443 synchronize by ggerganov
20m 29s gg/fix-kv-cache
gg/fix-kv-cache
20m 29s
whisper : fix excessive memory usage CI #3093: Pull request #2443 synchronize by ggerganov
1h 42m 8s gg/fix-kv-cache
gg/fix-kv-cache
1h 42m 8s
whisper : reduce memory overhead from unused input tensors CI #3092: Commit 1874968 pushed by ggerganov
1h 39m 57s gg/fix-kv-cache
gg/fix-kv-cache
1h 39m 57s
update dr_wav.h to newer version to fix _MSC_VER macro issues Publish Docker image #840: Pull request #2449 opened by RahulVadhyar
30m 14s RahulVadhyar:master
RahulVadhyar:master
30m 14s
update dr_wav.h to newer version to fix _MSC_VER macro issues CI #3091: Pull request #2449 opened by RahulVadhyar
2h 3m 16s RahulVadhyar:master
RahulVadhyar:master
2h 3m 16s
talk-llama : sync llama.cpp Publish Docker image #839: Commit ccc2547 pushed by ggerganov
2m 7s master
master
2m 7s