Skip to content

Actions: teleprint-me/llama.cpp

Nix CI

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
428 workflow runs
428 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

CUDA: faster q2_K, q3_K MMQ + int8 tensor cores (#7921)
Nix CI #689: Commit 76d66ee pushed by teleprint-me
June 14, 2024 16:42 14m 55s master
June 14, 2024 16:42 14m 55s
metal : utilize max shared memory for mul_mat_id (#7935)
Nix CI #688: Commit 66ef1ce pushed by teleprint-me
June 14, 2024 16:16 3m 36s master
June 14, 2024 16:16 3m 36s
[pull] master from ggerganov:master
Nix CI #682: Pull request #115 opened by pull bot
June 13, 2024 02:56 3m 27s ggerganov:master
June 13, 2024 02:56 3m 27s
CUDA: fix broken oob check for FA vec f32 kernel (#7904)
Nix CI #681: Commit 9635529 pushed by teleprint-me
June 12, 2024 17:44 3m 36s master
June 12, 2024 17:44 3m 36s
[pull] master from ggerganov:master
Nix CI #672: Pull request #114 opened by pull bot
June 11, 2024 14:15 5m 34s ggerganov:master
June 11, 2024 14:15 5m 34s
June 11, 2024 04:08 5m 9s
flake.lock: Update (#7838)
Nix CI #670: Commit 10ceba3 pushed by teleprint-me
June 10, 2024 06:39 3m 29s master
June 10, 2024 06:39 3m 29s
imatrix : handle partial entries (#7833)
Nix CI #669: Commit e95beeb pushed by teleprint-me
June 9, 2024 22:15 3m 37s master
June 9, 2024 22:15 3m 37s
[pull] master from ggerganov:master
Nix CI #667: Pull request #113 opened by pull bot
June 9, 2024 08:33 7m 35s ggerganov:master
June 9, 2024 08:33 7m 35s
convert-hf : match model part name prefix and suffix (#7687)
Nix CI #666: Commit 5795b94 pushed by teleprint-me
June 9, 2024 03:57 6m 9s master
June 9, 2024 03:57 6m 9s
[pull] master from ggerganov:master
Nix CI #662: Pull request #112 opened by pull bot
June 8, 2024 22:28 3m 31s ggerganov:master
June 8, 2024 22:28 3m 31s
[pull] master from ggerganov:master
Nix CI #661: Pull request #111 opened by pull bot
June 8, 2024 10:02 3m 31s ggerganov:master
June 8, 2024 10:02 3m 31s
vulkan : reuse parent extra for views (#7806)
Nix CI #660: Commit da799b4 pushed by teleprint-me
June 7, 2024 18:31 3m 30s master
June 7, 2024 18:31 3m 30s
[pull] master from ggerganov:master
Nix CI #655: Pull request #110 opened by pull bot
June 7, 2024 06:41 4m 2s ggerganov:master
June 7, 2024 06:41 4m 2s
server : fix --threads-http arg (#7801)
Nix CI #654: Commit ee459f4 pushed by teleprint-me
June 6, 2024 19:02 3m 32s master
June 6, 2024 19:02 3m 32s
Fix encoding in python scripts (#7733)
Nix CI #650: Commit 7672ade pushed by teleprint-me
June 5, 2024 20:06 3m 57s master
June 5, 2024 20:06 3m 57s
CUDA: refactor mmq, dmmv, mmvq (#7716)
Nix CI #649: Commit 7d1a378 pushed by teleprint-me
June 5, 2024 16:15 3m 34s master
June 5, 2024 16:15 3m 34s
[pull] master from ggerganov:master
Nix CI #645: Pull request #108 opened by pull bot
June 4, 2024 23:54 17m 8s ggerganov:master
June 4, 2024 23:54 17m 8s
readme : remove obsolete Zig instructions (#7471)
Nix CI #644: Commit 5ca0944 pushed by teleprint-me
June 4, 2024 17:40 16m 16s master
June 4, 2024 17:40 16m 16s
[pull] master from ggerganov:master
Nix CI #640: Pull request #107 opened by pull bot
June 4, 2024 11:01 3m 45s ggerganov:master
June 4, 2024 11:01 3m 45s
llama : offload to RPC in addition to other backends (#7640)
Nix CI #639: Commit bde7cd3 pushed by teleprint-me
June 3, 2024 17:04 5m 58s master
June 3, 2024 17:04 5m 58s
[pull] master from ggerganov:master
Nix CI #634: Pull request #106 opened by pull bot
June 3, 2024 08:34 5m 50s ggerganov:master
June 3, 2024 08:34 5m 50s
llama : avoid double token-to-piece cache (#7654)
Nix CI #633: Commit 549279d pushed by teleprint-me
June 3, 2024 07:37 22m 34s master
June 3, 2024 07:37 22m 34s
chore : add ignore rule for generated server themes (#7689)
Nix CI #632: Commit 7c4e5b7 pushed by teleprint-me
June 2, 2024 19:50 3m 38s master
June 2, 2024 19:50 3m 38s
Fix FlashAttention debug test, FP32 assert (#7684)
Nix CI #631: Commit e141ce6 pushed by teleprint-me
June 2, 2024 01:54 3m 32s master
June 2, 2024 01:54 3m 32s