Skip to content

Actions: fairydreaming/llama.cpp

Actions

Server

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
server.yml
13 workflow runs
13 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

Fix visionOS build and add CI (#12415) Server #45: Commit 0fd8487 pushed by fairydreaming
8m 11s master
master
8m 11s
[CANN]MUL_MAT optimization (#12382) Server #44: Commit 92a3913 pushed by fairydreaming
10m 28s master
master
10m 28s
ggml-cpu: Add CPU backend support for KleidiAI library (#11390) Server #43: Commit c5d91a7 pushed by fairydreaming
8m 7s master
master
8m 7s
server : (webui) migrate project to ReactJS with typescript (#11688) Server #42: Commit 2fb3c32 pushed by fairydreaming
7m 54s master
master
7m 54s
ci: simplify cmake build commands (#11548) Server #41: Commit 5bbc736 pushed by fairydreaming
9m 1s master
master
9m 1s
CPU/CUDA: fix (GQA) mul mat back, add CUDA support (#11380) Server #40: Commit 8137b4b pushed by fairydreaming
7m 40s master
master
7m 40s
minja: sync at https://github.com/google/minja/commit/0f5f7f2b3770e… Server #39: Commit c64d2be pushed by fairydreaming
7m 54s master
master
7m 54s
Add Jinja template support (#11016) Server #38: Commit 6171c9d pushed by fairydreaming
7m 42s master
master
7m 42s
common : disable KV cache shifting automatically for unsupported mode… Server #37: Commit 4b0c638 pushed by fairydreaming
4m 51s master
master
4m 51s
readme : add llama-swap to infrastructure section (#11032) Server #36: Commit a45433b pushed by fairydreaming
5m 15s master
master
5m 15s
fix: graceful shutdown for Docker images (#10815) Server #35: Commit 11e07fd pushed by fairydreaming
5m 43s master
master
5m 43s
vulkan: optimize and reenable split_k (#10637) Server #34: Commit cc98896 pushed by fairydreaming
10m 46s master
master
10m 46s
sycl : Reroute permuted mul_mats through oneMKL (#10408) Server #33: Commit 266b851 pushed by fairydreaming
4m 5s master
master
4m 5s