Skip to content

Actions: ngxson/llama.cpp

Actions

Publish Docker image

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
docker.yml
262 workflow run results
262 workflow run results

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

Fix missing file renames in Makefile due to changes in commit ae8de6d… Publish Docker image #512: Commit 3952a22 pushed by ngxson
42m 12s master
master
42m 12s
add cmake rvv support (#10411) Publish Docker image #511: Commit 42ae10b pushed by ngxson
43m 3s master
master
43m 3s
sync : ggml Publish Docker image #510: Commit 9fe0fb0 pushed by ngxson
30m 38s master
master
30m 38s
Add required ggml-base and backend libs to cmake pkg (#10407) Publish Docker image #509: Commit 2a11b6b pushed by ngxson
32m 0s master
master
32m 0s
cuda : fix CUDA_FLAGS not being applied (#10403) Publish Docker image #508: Commit 3ee6382 pushed by ngxson
31m 33s master
master
31m 33s
llama : add check for KV cache shifts (#10401) Publish Docker image #507: Commit 8e752a7 pushed by ngxson
31m 10s master
master
31m 10s
llama : add OLMo November 2024 support (#10394) Publish Docker image #506: Commit a88ad00 pushed by ngxson
31m 52s master
master
31m 52s
sycl : Add option to set the SYCL architecture for all targets (#10266) Publish Docker image #505: Commit 2a1507c pushed by ngxson
35m 42s master
master
35m 42s
vulkan: Optimize soft_max (#10301) Publish Docker image #504: Commit b3e5859 pushed by ngxson
32m 30s master
master
32m 30s
sycl: Revert MUL_MAT_OP support changes (#10385) Publish Docker image #503: Commit 557924f pushed by ngxson
33m 26s master
master
33m 26s
cuda : only use native when supported by cmake (#10389) Publish Docker image #502: Commit d3481e6 pushed by ngxson
32m 42s master
master
32m 42s
Vulkan: Fix device info output format specifiers (#10366) Publish Docker image #501: Commit 9b75f03 pushed by ngxson
43m 48s master
master
43m 48s
docker: use GGML_NATIVE=OFF (#10368) Publish Docker image #500: Commit 75207b3 pushed by ngxson
30m 54s master
master
30m 54s
CUDA: fix MMV kernel being used for FP16 src1 (#10357) Publish Docker image #499: Commit 76e9e58 pushed by ngxson
4m 15s master
master
4m 15s
llama : only use default buffer types for the KV cache (#10358) Publish Docker image #498: Commit be5cacc pushed by ngxson
3m 44s master
master
3m 44s
CUDA: remove DMMV, consolidate F16 mult mat vec (#10318) Publish Docker image #497: Commit c3ea58a pushed by ngxson
4m 19s master
master
4m 19s
ggml : fix possible buffer use after free in sched reserve (#9930) Publish Docker image #496: Commit eda7e1d pushed by ngxson
41m 9s master
master
41m 9s
llama/ex: remove --logdir argument (#10339) Publish Docker image #495: Commit 4e54be0 pushed by ngxson
31m 35s master
master
31m 35s
llamafile : fix include path (#0) Publish Docker image #494: Commit db4cfd5 pushed by ngxson
30m 47s master
master
30m 47s
server: (web UI) Add samplers sequence customization (#10255) Publish Docker image #493: Commit bcdb7a2 pushed by ngxson
32m 52s master
master
32m 52s
vulkan: Optimize some mat-vec mul quant shaders (#10296) Publish Docker image #492: Commit 772703c pushed by ngxson
33m 8s master
master
33m 8s
ggml : optimize Q4_0 into Q4_0_X_Y repack (#10324) Publish Docker image #491: Commit 1e58ee1 pushed by ngxson
34m 0s master
master
34m 0s
Make updates to fix issues with clang-cl builds while using AVX512 fl… Publish Docker image #490: Commit 74d73dc pushed by ngxson
34m 52s master
master
34m 52s
scripts: update compare-llama-bench.py (#10319) Publish Docker image #489: Commit 4047be7 pushed by ngxson
32m 32s master
master
32m 32s
cmake : fix ppc64 check (whisper/0) Publish Docker image #488: Commit 09ecbcb pushed by ngxson
34m 52s master
master
34m 52s