Skip to content

Actions: ggerganov/llama.cpp

Actions

Server

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
server.yml
6,531 workflow runs
6,531 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

llama: remove redundant loop when constructing ubatch (#9574) Server #6857: Commit ecd5d6b pushed by slaren
September 22, 2024 02:30 In progress master
master
September 22, 2024 02:30 In progress
RWKV v6: RWKV_WKV op CUDA implementation (#9454) Server #6856: Commit 2a63caa pushed by slaren
September 22, 2024 02:29 48m 58s master
master
September 22, 2024 02:29 48m 58s
RWKV v6: RWKV_WKV op CUDA implementation Server #6855: Pull request #9454 synchronize by MollySophia
September 22, 2024 01:17 24m 23s MollySophia:wkv-cuda
MollySophia:wkv-cuda
September 22, 2024 01:17 24m 23s
CUDA: enable Gemma FA for HIP/Pascal Server #6854: Pull request #9581 opened by JohannesGaessler
September 21, 2024 18:19 13m 52s JohannesGaessler:hip-enable-gemma-fattn
JohannesGaessler:hip-enable-gemma-fattn
September 21, 2024 18:19 13m 52s
Revert "[SYCL] fallback mmvq" Server #6853: Pull request #9579 opened by qnixsynapse
September 21, 2024 14:35 12m 46s qnixsynapse:revert-9088-sycl-fallback-mmvq
qnixsynapse:revert-9088-sycl-fallback-mmvq
September 21, 2024 14:35 12m 46s
ggml-alloc : fix list of allocated tensors with GGML_ALLOCATOR_DEBUG … Server #6852: Commit d09770c pushed by slaren
September 21, 2024 12:24 11m 8s master
master
September 21, 2024 12:24 11m 8s
CUDA: Enable K-shift operation for -ctk q8_0 (limited) Server #6851: Pull request #9571 synchronize by Nekotekina
September 21, 2024 07:54 10m 47s Nekotekina:kshift
Nekotekina:kshift
September 21, 2024 07:54 10m 47s
CUDA: Enable K-shift operation for -ctk q8_0 (limited) Server #6850: Pull request #9571 synchronize by Nekotekina
September 21, 2024 07:48 Action required Nekotekina:kshift
Nekotekina:kshift
September 21, 2024 07:48 Action required
server: disable context shift Server #6849: Pull request #9544 synchronize by VJHack
September 21, 2024 05:35 10m 33s VJHack:server-disable-context-shift
VJHack:server-disable-context-shift
September 21, 2024 05:35 10m 33s
llama: remove redundant loop when constructing ubatch Server #6848: Pull request #9574 opened by shankarg87
September 21, 2024 02:06 11m 19s shankarg87:ubatch_fix
shankarg87:ubatch_fix
September 21, 2024 02:06 11m 19s
ggml-alloc : fix list of allocated tensors with GGML_ALLOCATOR_DEBUG Server #6847: Pull request #9573 opened by slaren
September 21, 2024 01:39 11m 27s sl/fix-debug-alloc
sl/fix-debug-alloc
September 21, 2024 01:39 11m 27s
Update CUDA graph on scale change plus clear nodes/params (#9550) Server #6846: Commit 41f4778 pushed by slaren
September 21, 2024 00:41 32m 51s master
master
September 21, 2024 00:41 32m 51s
CUDA: Enable K-shift operation for -ctk q8_0 (limited) Server #6845: Pull request #9571 synchronize by Nekotekina
September 20, 2024 21:33 Action required Nekotekina:kshift
Nekotekina:kshift
September 20, 2024 21:33 Action required
server: disable context shift Server #6844: Pull request #9544 synchronize by VJHack
September 20, 2024 19:56 10m 59s VJHack:server-disable-context-shift
VJHack:server-disable-context-shift
September 20, 2024 19:56 10m 59s
server: disable context shift Server #6843: Pull request #9544 synchronize by VJHack
September 20, 2024 19:54 2m 15s VJHack:server-disable-context-shift
VJHack:server-disable-context-shift
September 20, 2024 19:54 2m 15s
CUDA: Enable K-shift operation for -ctk q8_0 (limited) Server #6842: Pull request #9571 opened by Nekotekina
September 20, 2024 19:11 Action required Nekotekina:kshift
Nekotekina:kshift
September 20, 2024 19:11 Action required
quantize : improve type name parsing (#9570) Server #6841: Commit 6335114 pushed by slaren
September 20, 2024 18:55 28m 6s master
master
September 20, 2024 18:55 28m 6s
quantize : improve type name parsing Server #6840: Pull request #9570 opened by slaren
September 20, 2024 18:16 44m 25s sl/fix-quantize-arg-parse
sl/fix-quantize-arg-parse
September 20, 2024 18:16 44m 25s
ggml : fix builds (#0) Server #6839: Commit d13edb1 pushed by ggerganov
September 20, 2024 18:15 12m 44s master
master
September 20, 2024 18:15 12m 44s
sync : ggml Server #6838: Pull request #9567 synchronize by ggerganov
September 20, 2024 17:36 11m 11s sync
sync
September 20, 2024 17:36 11m 11s
sync : ggml Server #6837: Pull request #9567 synchronize by ggerganov
September 20, 2024 17:13 11m 39s sync
sync
September 20, 2024 17:13 11m 39s
CUDA: fix sum.cu compilation for CUDA < 11.7 (#9562) Server #6836: Commit 5cb12f6 pushed by JohannesGaessler
September 20, 2024 16:35 11m 46s master
master
September 20, 2024 16:35 11m 46s
sync : ggml Server #6835: Pull request #9567 synchronize by ggerganov
September 20, 2024 16:13 12m 53s sync
sync
September 20, 2024 16:13 12m 53s
sync : ggml Server #6834: Pull request #9567 opened by ggerganov
September 20, 2024 16:10 2m 54s sync
sync
September 20, 2024 16:10 2m 54s
ggml: Add run-time detection of neon, i8mm and sve Server #6833: Pull request #9331 synchronize by eddnjjn
September 20, 2024 13:57 1h 31m 45s eddnjjn:cpu-runtime-feature-detection
eddnjjn:cpu-runtime-feature-detection
September 20, 2024 13:57 1h 31m 45s