Skip to content

Actions: Mozilla-Ocho/llamafile

Actions

All workflows

Actions

Loading...

Showing runs from all workflows
288 workflow runs
288 workflow runs
Event

Filter by event
Status

Filter by status
Branch
Actor

Filter by actor
github: add mention of strace and ftrace Pull Request Labeler #2: Pull request #449 synchronize by mofosyne
May 26, 2024 11:55 13s
May 26, 2024 11:55 13s
github: add mention of strace and ftrace Pull Request Labeler #1: Pull request #449 opened by mofosyne
May 26, 2024 11:54 18s
May 26, 2024 11:54 18s
Clarify 'man' as manual in README (#376) CI #248: Commit 564d9fb pushed by jart
May 8, 2024 11:57 46m 8s main
main
May 8, 2024 11:57 46m 8s
Sync with upstream llama.cpp project CI #247: Commit 94d0940 pushed by jart
May 8, 2024 05:31 47m 46s main
main
May 8, 2024 05:31 47m 46s
Fix issues with server send_embeddings function CI #246: Commit 0e2845a pushed by jart
May 8, 2024 04:48 45m 10s main
main
May 8, 2024 04:48 45m 10s
Faster AVX2 matrix multiplications for lgacy quants CI #245: Pull request #405 opened by ikawrakow
May 7, 2024 16:12 46m 35s ikawrakow:ik/new_legacy_mul_mat
ikawrakow:ik/new_legacy_mul_mat
May 7, 2024 16:12 46m 35s
Fix server multimodal statistics (#392) CI #243: Commit a2d159e pushed by jart
May 7, 2024 10:55 49m 59s main
main
May 7, 2024 10:55 49m 59s
Revert moondream vision language model support CI #242: Commit aa8c01a pushed by jart
May 7, 2024 06:22 2m 26s main
main
May 7, 2024 06:22 2m 26s
Faster AVX2 prompt processing for k-quants and IQ4_XS (#394) CI #241: Commit e6532f7 pushed by jart
May 7, 2024 02:58 2m 18s main
main
May 7, 2024 02:58 2m 18s
Fix vim modelines (#351) CI #239: Commit 911d58f pushed by jart
May 6, 2024 18:29 2m 33s main
main
May 6, 2024 18:29 2m 33s
More conservative strong/em markdown matcher (#352) CI #237: Commit eecbf89 pushed by jart
May 6, 2024 18:26 3m 1s main
main
May 6, 2024 18:26 3m 1s
Add special tokens to server llama_decode() inputs CI #236: Commit 7900294 pushed by jart
May 4, 2024 03:06 2m 28s main
main
May 4, 2024 03:06 2m 28s
Add --precise and --fast flags CI #235: Commit bbae0f6 pushed by jart
May 3, 2024 15:53 2m 35s main
main
May 3, 2024 15:53 2m 35s
Add --precise and --fast flags CI #234: Commit 62381a7 pushed by jart
May 3, 2024 15:51 3m 40s main
main
May 3, 2024 15:51 3m 40s
Faster AVX2 prompt processing for k-quants and IQ4_XS CI #233: Pull request #394 opened by ikawrakow
May 3, 2024 12:33 2m 54s ikawrakow:ik/iqk_mul_mat
ikawrakow:ik/iqk_mul_mat
May 3, 2024 12:33 2m 54s
Speed up prediction on CPUs with many cores CI #232: Commit 89c189e pushed by jart
May 3, 2024 05:23 2m 58s main
main
May 3, 2024 05:23 2m 58s
Disable an unintended integrity check CI #230: Commit 2b4da98 pushed by jart
May 2, 2024 07:13 3m 25s main
main
May 2, 2024 07:13 3m 25s
Make GGML vector ops go faster across hardware CI #229: Commit c9d7393 pushed by jart
May 2, 2024 05:50 2m 47s main
main
May 2, 2024 05:50 2m 47s
Upgrade to latest llama.cpp code CI #228: Commit 0bdea60 pushed by jart
May 1, 2024 05:08 2m 31s main
main
May 1, 2024 05:08 2m 31s
Add Kahan summation to tinyBLAS Q8/Q4 on ARM CI #227: Commit 2af3b88 pushed by jart
April 30, 2024 21:32 2m 37s main
main
April 30, 2024 21:32 2m 37s
Synchronize after every op CI #226: Commit 9cf7363 pushed by jart
April 30, 2024 03:35 2m 29s main
main
April 30, 2024 03:35 2m 29s
Synchronize after every op CI #225: Commit 622924c pushed by jart
April 30, 2024 03:32 2m 30s main
main
April 30, 2024 03:32 2m 30s
Synchronize after every op CI #224: Commit cbb94e5 pushed by jart
April 30, 2024 03:31 3m 9s main
main
April 30, 2024 03:31 3m 9s
Use 4.7x fewer synchronization barriers in GGML CI #223: Commit bd8c0de pushed by jart
April 29, 2024 05:43 2m 45s main
main
April 29, 2024 05:43 2m 45s
Rewrite synchronization primitives CI #222: Commit 6162004 pushed by jart
April 28, 2024 16:29 1m 57s main
main
April 28, 2024 16:29 1m 57s