Skip to content

Actions: ggerganov/llama.cpp

Actions

Publish Docker image

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
docker.yml
9,850 workflow runs
9,850 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

docker: use GGML_NATIVE=OFF (#10368) Publish Docker image #14728: Commit 75207b3 pushed by JohannesGaessler
November 17, 2024 23:21 32m 9s master
master
November 17, 2024 23:21 32m 9s
CUDA: fix MMV kernel being used for FP16 src1 (#10357) Publish Docker image #14727: Commit 76e9e58 pushed by JohannesGaessler
November 17, 2024 22:20 23m 3s master
master
November 17, 2024 22:20 23m 3s
llama : only use default buffer types for the KV cache (#10358) Publish Docker image #14726: Commit be5cacc pushed by slaren
November 17, 2024 11:25 24m 59s master
master
November 17, 2024 11:25 24m 59s
ggml : fix undefined reference to 'getcpu' (#10354) Publish Docker image #14725: Commit a431782 pushed by ggerganov
November 17, 2024 08:39 58m 59s master
master
November 17, 2024 08:39 58m 59s
CUDA: remove DMMV, consolidate F16 mult mat vec (#10318) Publish Docker image #14724: Commit c3ea58a pushed by JohannesGaessler
November 17, 2024 08:09 51m 43s master
master
November 17, 2024 08:09 51m 43s
CMake: default to -arch=native for CUDA build (#10320) Publish Docker image #14723: Commit 467576b pushed by JohannesGaessler
November 17, 2024 08:06 42m 43s master
master
November 17, 2024 08:06 42m 43s
ggml : fix possible buffer use after free in sched reserve (#9930) Publish Docker image #14722: Commit eda7e1d pushed by ggerganov
November 17, 2024 06:31 1h 6m 7s master
master
November 17, 2024 06:31 1h 6m 7s
ggml : inttypes.h -> cinttypes (#0) Publish Docker image #14721: Commit 24203e9 pushed by ggerganov
November 17, 2024 06:30 32m 23s master
master
November 17, 2024 06:30 32m 23s
llama/ex: remove --logdir argument (#10339) Publish Docker image #14720: Commit 4e54be0 pushed by JohannesGaessler
November 16, 2024 22:00 1h 22m 31s master
master
November 16, 2024 22:00 1h 22m 31s
llamafile : fix include path (#0) Publish Docker image #14719: Commit db4cfd5 pushed by ggerganov
November 16, 2024 18:36 2h 14m 41s master
master
November 16, 2024 18:36 2h 14m 41s
server: (web UI) Add samplers sequence customization (#10255) Publish Docker image #14718: Commit bcdb7a2 pushed by ngxson
November 16, 2024 13:26 36m 58s master
master
November 16, 2024 13:26 36m 58s
vulkan: Optimize some mat-vec mul quant shaders (#10296) Publish Docker image #14717: Commit 772703c pushed by 0cc4m
November 16, 2024 06:27 38m 43s master
master
November 16, 2024 06:27 38m 43s
ggml : optimize Q4_0 into Q4_0_X_Y repack (#10324) Publish Docker image #14716: Commit 1e58ee1 pushed by slaren
November 16, 2024 00:53 1h 31m 39s master
master
November 16, 2024 00:53 1h 31m 39s
llama : save number of parameters and the size in llama_model (#10286) Publish Docker image #14715: Commit 89e4caa pushed by slaren
November 16, 2024 00:42 54m 54s master
master
November 16, 2024 00:42 54m 54s
Make updates to fix issues with clang-cl builds while using AVX512 fl… Publish Docker image #14714: Commit 74d73dc pushed by slaren
November 15, 2024 21:27 1h 34m 20s master
master
November 15, 2024 21:27 1h 34m 20s
ggml : fix some build issues Publish Docker image #14713: Commit 883d206 pushed by ggerganov
November 15, 2024 19:45 2h 8m 26s master
master
November 15, 2024 19:45 2h 8m 26s
cmake : fix ppc64 check (whisper/0) Publish Docker image #14712: Commit 09ecbcb pushed by ggerganov
November 15, 2024 13:44 5h 40m 50s master
master
November 15, 2024 13:44 5h 40m 50s
AVX BF16 and single scale quant optimizations (#10212) Publish Docker image #14711: Commit 1842922 pushed by slaren
November 15, 2024 11:48 5h 46m 54s master
master
November 15, 2024 11:48 5h 46m 54s
sycl: Update Intel docker images to use DPC++ 2025.0 (#10305) Publish Docker image #14710: Commit 57f8355 pushed by ggerganov
November 15, 2024 11:10 5h 2m 1s master
master
November 15, 2024 11:10 5h 2m 1s
server : (web UI) add copy button for code block, fix api key (#10242) Publish Docker image #14709: Commit 9901068 pushed by ngxson
November 15, 2024 09:48 3h 51m 51s master
master
November 15, 2024 09:48 3h 51m 51s
cann: dockerfile and doc adjustment (#10302) Publish Docker image #14708: Commit 231f936 pushed by hipudding
November 15, 2024 07:09 1h 3m 26s master
master
November 15, 2024 07:09 1h 3m 26s
sycl: Use syclcompat::dp4a (#10267) Publish Docker image #14707: Commit 5a54af4 pushed by airMeng
November 15, 2024 03:09 5m 10s master
master
November 15, 2024 03:09 5m 10s
backend cpu: add online flow for aarch64 Q4_0 GEMV/GEMM kernels (#9921) Publish Docker image #14706: Commit 1607a5e pushed by slaren
November 15, 2024 00:28 30m 52s master
master
November 15, 2024 00:28 30m 52s
ggml : build backends as libraries (#10256) Publish Docker image #14705: Commit ae8de6d pushed by slaren
November 14, 2024 17:04 59m 39s master
master
November 14, 2024 17:04 59m 39s
CUDA: no -sm row for very small matrices (#10185) Publish Docker image #14704: Commit 4a8ccb3 pushed by JohannesGaessler
November 14, 2024 12:00 31m 46s master
master
November 14, 2024 12:00 31m 46s