Skip to content

Actions: ngxson/llama.cpp

Actions

Server

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
server.yml
385 workflow run results
385 workflow run results

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

Server Server #838: Manually run by ngxson
6m 12s xsn/cancellable_request
xsn/cancellable_request
6m 12s
Server Server #837: Manually run by ngxson
7m 26s xsn/cancellable_request
xsn/cancellable_request
7m 26s
Server Server #836: Manually run by ngxson
6m 32s xsn/cancellable_request
xsn/cancellable_request
6m 32s
llama.android: add field formatChat to control whether to parse speci… Server #835: Commit 3edfa7d pushed by ngxson
5m 22s master
master
5m 22s
rpc : early register backend devices (#11262) Server #834: Commit 667d728 pushed by ngxson
5m 20s master
master
5m 20s
vocab : fix double-eos check (#11273) Server #833: Commit a133566 pushed by ngxson
17m 9s master
master
17m 9s
llama : fix deprecation message: vocabable -> vocab (#11269) Server #832: Commit 960ec65 pushed by ngxson
6m 35s master
master
6m 35s
vulkan: support copy from f32 to q4_0/q4_1/q5_0/q5_1/q8_0/iq4_nl (#11… Server #831: Commit bd38dde pushed by ngxson
11m 19s master
master
11m 19s
CUDA: backwards pass for misc. ops, add tests (#11257) Server #830: Commit 9c8dcef pushed by ngxson
5m 47s master
master
5m 47s
llama : add llama_model_load_from_splits (#11255) Server #829: Commit 681149c pushed by ngxson
5m 15s master
master
5m 15s
ggml: aarch64: implement SVE kernels for q4_K_q8_K vector dot (#11227) Server #828: Commit c67cc98 pushed by ngxson
6m 0s master
master
6m 0s
fix: ggml: fix vulkan-shaders-gen build (#10448) Server #827: Commit 1d85043 pushed by ngxson
12m 41s master
master
12m 41s
RoPE: fix back, CUDA support for back + noncont. (#11240) Server #826: Commit 432df2d pushed by ngxson
6m 20s master
master
6m 20s
SYCL: Add gated linear attention kernel (#11175) Server #825: Commit f446c2c pushed by ngxson
6m 13s master
master
6m 13s
server : Improve code snippets direction between RTL text (#11221) Server #824: Commit c5bf0d1 pushed by ngxson
5m 46s master
master
5m 46s
Refactor test-chat-template.cpp (#11224) Server #823: Commit 091592d pushed by ngxson
5m 40s master
master
5m 40s
server : (UI) Improve messages bubble shape in RTL (#11220) Server #822: Commit 504af20 pushed by ngxson
10m 3s master
master
10m 3s
cli : auto activate conversation mode if chat template is available (… Server #821: Commit 84a4481 pushed by ngxson
6m 13s master
master
6m 13s
cuda : CUDA Graph Compute Function Refactor (precursor for performanc… Server #820: Commit 39509fb pushed by ngxson
6m 9s master
master
6m 9s
server : (UI) Support for RTL text as models input or output (#11208) Server #819: Commit 437e05f pushed by ngxson
4m 57s master
master
4m 57s
common : support tag-based --hf-repo like on ollama (#11195) Server #818: Commit 00b4c3d pushed by ngxson
6m 57s master
master
6m 57s
llama : remove 'd' from bad special token log (#11212) Server #817: Commit 8f70fc3 pushed by ngxson
5m 32s master
master
5m 32s
ggml : do not define GGML_USE_CUDA when building with GGML_BACKEND_DL… Server #816: Commit 1244cdc pushed by ngxson
5m 4s master
master
5m 4s
Reset color before we exit (#11205) Server #815: Commit 924518e pushed by ngxson
5m 45s master
master
5m 45s
llama : fix chat template gguf key (#11201) Server #814: Commit 9a48399 pushed by ngxson
4m 55s master
master
4m 55s