Skip to content

Actions: ngxson/llama.cpp

Actions

Publish Docker image

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
docker.yml
120 workflow run results
120 workflow run results

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

ggml : add backend registry / device interfaces to BLAS backend (#9752) Publish Docker image #371: Commit 6374743 pushed by ngxson
32m 48s master
master
32m 48s
Update building for Android (#9672) Publish Docker image #370: Commit f1af42f pushed by ngxson
51m 0s master
master
51m 0s
metal : single allocation of encode_async block (#9747) Publish Docker image #369: Commit 96b6912 pushed by ngxson
42m 31s master
master
42m 31s
sync : llama.cpp Publish Docker image #368: Commit b6d6c52 pushed by ngxson
30m 43s master
master
30m 43s
rerank : use [SEP] token instead of [BOS] (#9737) Publish Docker image #367: Commit 8c475b9 pushed by ngxson
32m 13s master
master
32m 13s
sync : ggml Publish Docker image #366: Commit 1788077 pushed by ngxson
32m 25s master
master
32m 25s
Fixed RNG seed docs (#9723) Publish Docker image #365: Commit 133c7b4 pushed by ngxson
32m 11s master
master
32m 11s
metal : remove abort (skip) (ggml/0) Publish Docker image #364: Commit d5ed2b9 pushed by ngxson
41m 13s master
master
41m 13s
ggml-backend : add device description to CPU backend (#9720) Publish Docker image #363: Commit a7ad553 pushed by ngxson
31m 56s master
master
31m 56s
rpc : enable vulkan (#9714) Publish Docker image #362: Commit 841713e pushed by ngxson
32m 47s master
master
32m 47s
Fixed dequant precision issues in Q4_1 and Q5_1 (#9711) Publish Docker image #361: Commit 5639971 pushed by ngxson
32m 35s master
master
32m 35s
ggml-backend : add device and backend reg interfaces (#9707) Publish Docker image #360: Commit c83ad6d pushed by ngxson
30m 38s master
master
30m 38s
llama : reduce compile time and binary size (#9712) Publish Docker image #359: Commit a39ab21 pushed by ngxson
33m 6s master
master
33m 6s
[SYCL] Initial cmake support of SYCL for AMD GPUs (#9658) Publish Docker image #358: Commit f536f4c pushed by ngxson
32m 53s master
master
32m 53s
vulkan : do not use tensor->extra (#9407) Publish Docker image #357: Commit 00b7317 pushed by ngxson
47m 46s master
master
47m 46s
gguf-split : improve --split and --merge logic (#9619) Publish Docker image #356: Commit 76b37d1 pushed by ngxson
32m 3s master
master
32m 3s
sync : ggml Publish Docker image #355: Commit f1b8c42 pushed by ngxson
48m 35s master
master
48m 35s
llama : print correct model type for Llama 3.2 1B and 3B Publish Docker image #354: Commit a90484c pushed by ngxson
39m 7s master
master
39m 7s
Fix Docker ROCM builds, use AMDGPU_TARGETS instead of GPU_TARGETS (#9… Publish Docker image #353: Commit 6f1d9d7 pushed by ngxson
31m 41s master
master
31m 41s
console : utf-8 fix for windows stdin (#9690) Publish Docker image #352: Commit 8277a81 pushed by ngxson
32m 25s master
master
32m 25s
ggml : define missing HWCAP flags (#9684) Publish Docker image #351: Commit c919d5d pushed by ngxson
32m 14s master
master
32m 14s
common : ensure llama_batch size does not exceed max size (#9668) Publish Docker image #350: Commit faac0ba pushed by ngxson
33m 38s master
master
33m 38s
test-backend-ops : use flops for some performance tests (#9657) Publish Docker image #349: Commit 1b2f992 pushed by ngxson
32m 25s master
master
32m 25s
Enable use to the rebar feature to upload buffers to the device. (#9251) Publish Docker image #348: Commit 89f9944 pushed by ngxson
47m 16s master
master
47m 16s
cmake : add option for common library (#9661) Publish Docker image #347: Commit 44f59b4 pushed by ngxson
36m 33s master
master
36m 33s