Skip to content

Actions: ggerganov/llama.cpp

Actions

CI

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
build.yml
11,692 workflow runs
11,692 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

Add Falcon3 support and Fix issue #10875 CI #17766: Pull request #10883 opened by mokeddembillel
December 18, 2024 05:31 15m 35s mokeddembillel:falcon3_integration
mokeddembillel:falcon3_integration
December 18, 2024 05:31 15m 35s
SYCL: Migrate away from deprecated ggml_tensor->backend CI #17765: Pull request #10840 synchronize by qnixsynapse
December 18, 2024 04:01 22m 38s qnixsynapse:buffer_migrate
qnixsynapse:buffer_migrate
December 18, 2024 04:01 22m 38s
Revert "llama : add Falcon3 support (#10864)" (#10876) CI #17764: Commit 4da69d1 pushed by slaren
December 18, 2024 00:36 39m 14s master
master
December 18, 2024 00:36 39m 14s
Revert "Add Falcon3 model support" CI #17763: Pull request #10876 opened by slaren
December 17, 2024 22:31 46m 28s revert-10864-falcon3_integration
revert-10864-falcon3_integration
December 17, 2024 22:31 46m 28s
Use model->gguf_kv for loading the template instead of using the C AP… CI #17762: Commit d62b532 pushed by slaren
December 17, 2024 22:24 53m 33s master
master
December 17, 2024 22:24 53m 33s
server : (embeddings) using same format for "input" and "content" CI #17761: Pull request #10872 synchronize by ngxson
December 17, 2024 21:29 9m 31s ngxson:xsn/embedding_input
ngxson:xsn/embedding_input
December 17, 2024 21:29 9m 31s
server : (embeddings) using same format for "input" and "content" CI #17760: Pull request #10872 synchronize by ngxson
December 17, 2024 20:50 38m 24s ngxson:xsn/embedding_input
ngxson:xsn/embedding_input
December 17, 2024 20:50 38m 24s
ggml-cpu: replace NEON asm with intrinsics in ggml_gemv_q4_0_4x8_q8_0() CI #17759: Pull request #10874 opened by angt
December 17, 2024 20:47 52m 32s angt:ggml-cpu-replace-neon-asm-with-intrinsics-in-ggml_gemv_q4_0_4x8_q8_0
angt:ggml-cpu-replace-neon-asm-with-intrinsics-in-ggml_gemv_q4_0_4x8_q8_0
December 17, 2024 20:47 52m 32s
llama: Ensure KV cache is fully defragmented. CI #17758: Pull request #10873 opened by jessegross
December 17, 2024 20:46 43m 48s jessegross:kv_defrag
jessegross:kv_defrag
December 17, 2024 20:46 43m 48s
server : (embeddings) using same format for "input" and "content" CI #17757: Pull request #10872 opened by ngxson
December 17, 2024 20:37 13m 50s ngxson:xsn/embedding_input
ngxson:xsn/embedding_input
December 17, 2024 20:37 13m 50s
server : add "tokens" output CI #17756: Pull request #10853 synchronize by ggerganov
December 17, 2024 19:44 1h 50m 42s gg/server-content-tokens
gg/server-content-tokens
December 17, 2024 19:44 1h 50m 42s
Use model->gguf_kv for loading the template instead of using the C API. CI #17755: Pull request #10868 synchronize by dranger003
December 17, 2024 19:00 2h 31m 12s dranger003:master
dranger003:master
December 17, 2024 19:00 2h 31m 12s
Improve progress bar CI #17754: Pull request #10821 synchronize by ericcurtin
December 17, 2024 19:00 1h 40m 38s ericcurtin:progress-bar
ericcurtin:progress-bar
December 17, 2024 19:00 1h 40m 38s
tests: add tests for GGUF (#10830) CI #17753: Commit 081b29b pushed by JohannesGaessler
December 17, 2024 18:09 3h 16m 9s master
master
December 17, 2024 18:09 3h 16m 9s
Use model->gguf_kv for loading the template instead of using the C API. CI #17752: Pull request #10868 synchronize by dranger003
December 17, 2024 17:23 1h 37m 9s dranger003:master
dranger003:master
December 17, 2024 17:23 1h 37m 9s
sync : ggml CI #17751: Commit 5437d4a pushed by ggerganov
December 17, 2024 16:36 3h 51m 53s master
master
December 17, 2024 16:36 3h 51m 53s
ggml : update ggml_backend_cpu_device_supports_op (#10867) CI #17750: Commit 0006f5a pushed by ggerganov
December 17, 2024 16:35 3h 44m 12s master
master
December 17, 2024 16:35 3h 44m 12s
Improve progress bar CI #17749: Pull request #10821 synchronize by ericcurtin
December 17, 2024 16:10 1h 17m 13s ericcurtin:progress-bar
ericcurtin:progress-bar
December 17, 2024 16:10 1h 17m 13s
ggml : update ggml_backend_cpu_device_supports_op CI #17748: Pull request #10867 synchronize by ggerganov
December 17, 2024 16:09 54m 56s gg/cpu-fix-cpy-iq
gg/cpu-fix-cpy-iq
December 17, 2024 16:09 54m 56s
Use model->gguf_kv for loading the template instead of using the C API. CI #17747: Pull request #10868 opened by dranger003
December 17, 2024 16:06 52m 7s dranger003:master
dranger003:master
December 17, 2024 16:06 52m 7s
ggml : update ggml_backend_cpu_device_supports_op CI #17746: Pull request #10867 synchronize by ggerganov
December 17, 2024 16:05 4m 1s gg/cpu-fix-cpy-iq
gg/cpu-fix-cpy-iq
December 17, 2024 16:05 4m 1s
server : fill usage info in embeddings and rerank responses (#10852) CI #17745: Commit 05c3a44 pushed by ggerganov
December 17, 2024 16:00 2h 55m 22s master
master
December 17, 2024 16:00 2h 55m 22s
ggml : update ggml_backend_cpu_device_supports_op CI #17744: Pull request #10867 opened by ggerganov
December 17, 2024 15:57 8m 57s gg/cpu-fix-cpy-iq
gg/cpu-fix-cpy-iq
December 17, 2024 15:57 8m 57s
llama : add Falcon3 support (#10864) CI #17742: Commit 382bc7f pushed by ggerganov
December 17, 2024 15:24 1h 7m 34s master
master
December 17, 2024 15:24 1h 7m 34s
tts : add OuteTTS support CI #17741: Pull request #10784 synchronize by ggerganov
December 17, 2024 14:35 26m 38s gg/tts-add-outetts
gg/tts-add-outetts
December 17, 2024 14:35 26m 38s