Skip to content

Actions: ngxson/llama.cpp

Actions

Server

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
server.yml
1,378 workflow run results
1,378 workflow run results

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

scripts: benchmark for HTTP server throughput (#14668) Server #1817: Commit 494c589 pushed by ngxson
19m 16s master
master
19m 16s
SYCL: use 1D kernel for set_rows (#14618) Server #1816: Commit 0f4c6ec pushed by ngxson
15m 7s master
master
15m 7s
llama : add jinja template for rwkv-world (#14665) Server #1815: Commit 0d92267 pushed by ngxson
12m 2s master
master
12m 2s
quantize : fix minor logic flaw in --tensor-type (#14572) Server #1814: Commit 982e347 pushed by ngxson
11m 21s master
master
11m 21s
cuda : add set rows for bf16 (#14664) Server #1813: Commit 923e3ea pushed by ngxson
11m 49s master
master
11m 49s
cuda : add ELU support (#14657) Server #1812: Commit e743cdd pushed by ngxson
16m 4s master
master
16m 4s
ggml : add build-time message to remind about ggml_set_rows (#14661) Server #1811: Commit 05fec5b pushed by ngxson
14m 15s master
master
14m 15s
metal : Add missing unary ops Metal support (#14660) Server #1810: Commit dcf7f2e pushed by ngxson
11m 25s master
master
11m 25s
tests : cover lfm2 cases in test_ssm_conv (#14651) Server #1809: Commit c31e606 pushed by ngxson
11m 45s master
master
11m 45s
CUDA: add set rows for f32 and f16 (#14551) Server #1808: Commit 7de5c7c pushed by ngxson
11m 51s master
master
11m 51s
vulkan : remove unused vars (#0) Server #1807: Commit 3120413 pushed by ngxson
11m 36s master
master
11m 36s
server : fix pooled embedding output (#14645) Server #1806: Commit 0c1df14 pushed by ngxson
40m 29s master
master
40m 29s
vulkan: support SET_ROWS (#14587) Server #1805: Commit b3ad3a0 pushed by ngxson
11m 22s master
master
11m 22s
vulkan: optimizations for deepseek prompt processing (#14555) Server #1804: Commit 98197e5 pushed by ngxson
14m 2s master
master
14m 2s
model : support LiquidAI LFM2 hybrid family (#14620) Server #1803: Commit f5e96b3 pushed by ngxson
12m 0s master
master
12m 0s
HIP : Add HIP 7.0+ compatibility for hipBLAS compute types (#14634) Server #1802: Commit 756aa10 pushed by ngxson
12m 51s master
master
12m 51s
llama : move enum llama_vocab_pre_type to implementation (#14631) Server #1801: Commit 0d5375d pushed by ngxson
12m 25s master
master
12m 25s
vocab : add midm-2.0 model pre-tokenizer (#14626) Server #1800: Commit 576c82e pushed by ngxson
12m 18s master
master
12m 18s
model : Granite Four (#13550) Server #1799: Commit 0aedae0 pushed by ngxson
11m 27s master
master
11m 27s
opencl: add tiled mul_mat_f16_f32 (#14535) Server #1798: Commit 6bdda13 pushed by ngxson
12m 29s master
master
12m 29s
opencl: add set_rows for f16 and f32 (#14547) Server #1797: Commit 0b88557 pushed by ngxson
11m 13s master
master
11m 13s
Smoldocling support (#14597) Server #1796: Commit 4bb625b pushed by ngxson
11m 25s master
master
11m 25s
Docs: script to auto-generate ggml operations docs (#14598) Server #1795: Commit 11ee0fe pushed by ngxson
11m 37s master
master
11m 37s
cmake : do not search for curl libraries by ourselves (#14613) Server #1794: Commit a457551 pushed by ngxson
11m 25s master
master
11m 25s
SYCL: Initial set_rows kernel implementation (#14562) Server #1793: Commit 704bb7a pushed by ngxson
11m 24s master
master
11m 24s