Skip to content

Actions: ggml-org/llama.cpp

Actions

CI

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
build.yml
6,786 workflow run results
6,786 workflow run results

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

Add proper implementation of ollama's /api/chat CI #22922: Pull request #13777 opened by R-Dson
49m 26s R-Dson:master
R-Dson:master
49m 26s
kv-cache : refactor + add llama_memory_state_i CI #22921: Pull request #13746 synchronize by ggerganov
35m 59s gg/kv-cache-simplify-part3
gg/kv-cache-simplify-part3
35m 59s
rpc : Fix build on OpenBSD (#13541) CI #22920: Commit c508256 pushed by rgerganov
1h 6m 12s master
master
1h 6m 12s
ggml-backend: backend-agnostic tensor parallelism CI #22919: Pull request #13776 opened by JohannesGaessler
1h 5m 5s JohannesGaessler:backend-tensor-parallel
JohannesGaessler:backend-tensor-parallel
1h 5m 5s
mtmd : add support for Qwen2-Audio and SeaLLM-Audio (#13760) CI #22918: Commit 40aaa8a pushed by ngxson
1h 2m 53s master
master
1h 2m 53s
tests : improve UGM tokenizer test coverage CI #22917: Pull request #13773 opened by CISC
46m 54s cisc/test-coverage-ugm-tokenizer
cisc/test-coverage-ugm-tokenizer
46m 54s
server: add --reasoning-budget 0 to disable thinking (incl. qwen3 w/ enable_thinking:false) CI #22916: Pull request #13771 synchronize by ochafik
57m 17s ochafik:enable-thinking
ochafik:enable-thinking
57m 17s
server: add --reasoning-budget 0 to disable thinking (incl. qwen3 w/ enable_thinking:false) CI #22915: Pull request #13771 synchronize by ochafik
2m 58s ochafik:enable-thinking
ochafik:enable-thinking
2m 58s
ggml : add ggml_fill() CI #22914: Pull request #13772 synchronize by ngxson
1h 0m 6s ngxson:xsn/ggml_fill
ngxson:xsn/ggml_fill
1h 0m 6s
server: fix/test add_generation_prompt (#13770) CI #22913: Commit d785f9c pushed by ochafik
1h 34m 24s master
master
1h 34m 24s
ggml : add ggml_fill() CI #22912: Pull request #13772 synchronize by ngxson
34m 7s ngxson:xsn/ggml_fill
ngxson:xsn/ggml_fill
34m 7s
server: add --reasoning-budget 0 to disable thinking (incl. qwen3 w/ enable_thinking:false) CI #22911: Pull request #13771 synchronize by ochafik
1h 20m 15s ochafik:enable-thinking
ochafik:enable-thinking
1h 20m 15s
ggml : add ggml_fill() CI #22910: Pull request #13772 opened by ngxson
6m 24s ngxson:xsn/ggml_fill
ngxson:xsn/ggml_fill
6m 24s
server: add --reasoning-budget 0 to disable thinking (incl. qwen3 w/ enable_thinking:false) CI #22909: Pull request #13771 synchronize by ochafik
36m 49s ochafik:enable-thinking
ochafik:enable-thinking
36m 49s
server: add --reasoning-budget 0 to disable thinking (incl. qwen3 w/ enable_thinking:false) CI #22908: Pull request #13771 synchronize by ochafik
16m 56s ochafik:enable-thinking
ochafik:enable-thinking
16m 56s
mtmd : add support for Qwen2-Audio and SeaLLM-Audio CI #22907: Pull request #13760 synchronize by ngxson
2h 3m 35s ngxson:xsn/qwen2audio
ngxson:xsn/qwen2audio
2h 3m 35s
Support jinja extra template kwargs (Qwen3 enable_thinking feature), from command line and from client CI #22906: Pull request #13196 synchronize by matteoserva
2h 11m 3s matteoserva:enable_thinking
matteoserva:enable_thinking
2h 11m 3s
llama : add support for Qwen3 MoE tied word embeddings (#13768) CI #22905: Commit 4032ca4 pushed by CISC
1h 43m 17s master
master
1h 43m 17s
kv-cache : refactor + add llama_memory_state_i CI #22904: Pull request #13746 synchronize by ggerganov
1h 58m 34s gg/kv-cache-simplify-part3
gg/kv-cache-simplify-part3
1h 58m 34s
llama : try loading tensors with pre-computed hashes CI #22902: Pull request #13106 synchronize by rgerganov
1h 31m 17s rgerganov:rpc-load-tensor
rgerganov:rpc-load-tensor
1h 31m 17s
server: add --reasoning-budget 0 to disable thinking (incl. qwen3 w/ enable_thinking:false) CI #22901: Pull request #13771 synchronize by ochafik
37m 1s ochafik:enable-thinking
ochafik:enable-thinking
37m 1s
server: add --reasoning-budget 0 to disable thinking (incl. qwen3 w/ enable_thinking:false) CI #22900: Pull request #13771 synchronize by ochafik
4m 16s ochafik:enable-thinking
ochafik:enable-thinking
4m 16s
server: add --reasoning-budget 0 to disable thinking (incl. qwen3 w/ enable_thinking:false) CI #22899: Pull request #13771 opened by ochafik
1m 11s ochafik:enable-thinking
ochafik:enable-thinking
1m 11s
server: fix/test add_generation_prompt param CI #22898: Pull request #13770 opened by ochafik
1h 12m 27s ochafik:fix-gen-prompt
ochafik:fix-gen-prompt
1h 12m 27s
SYCL: revert "sycl: simplify bin_bcast_kernel (#13383)" (#13752) CI #22897: Commit 515fdbf pushed by ggerganov
58m 51s master
master
58m 51s