Skip to content

Actions: ggml-org/llama.cpp

Actions

CI

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
build.yml
4,024 workflow run results
4,024 workflow run results

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

llama : refactor llama_kv_cache, llama_context and llm_build_context CI #19870: Pull request #11213 synchronize by ggerganov
2m 36s gg/llama-kv-cache
gg/llama-kv-cache
2m 36s
ggml : upgrade init_tensor API to return a ggml_status (#11854) CI #19869: Commit 70680c4 pushed by slaren
55m 12s master
master
55m 12s
sycl: cleanup oneDNN related code CI #19868: Pull request #12097 synchronize by sgeor255
43m 23s sgeor255:svet/llama-onednn
sgeor255:svet/llama-onednn
43m 23s
CUDA: compress-mode size CI #19866: Pull request #12029 synchronize by Green-Sky
42m 47s Green-Sky:cuda_compress
Green-Sky:cuda_compress
42m 47s
Adding UTF-8 support to linenoise.cpp CI #19865: Pull request #12111 opened by ericcurtin
40m 2s llama-run-utf-8
llama-run-utf-8
40m 2s
llama : add Phi-4-mini support (supersede #12099) (#12108) CI #19864: Commit c43a3e7 pushed by ngxson
42m 32s master
master
42m 32s
sync : ggml CI #19862: Pull request #12104 synchronize by ggerganov
39m 29s sync-ggml-25-02-28
sync-ggml-25-02-28
39m 29s
llama : add Phi-4-mini support (supersede #12099) CI #19861: Pull request #12108 synchronize by ngxson
41m 47s xsn/phi-4
xsn/phi-4
41m 47s
llama : add Phi-4-mini support (supersede #12099) CI #19860: Pull request #12108 opened by ngxson
2m 38s xsn/phi-4
xsn/phi-4
2m 38s
llama : refactor llama_kv_cache, llama_context and llm_build_context CI #19859: Pull request #11213 synchronize by ggerganov
39m 36s gg/llama-kv-cache
gg/llama-kv-cache
39m 36s
vulkan: add specific MMV kernels for IQ2 and IQ3 quants + optimizatio… CI #19858: Commit 438a839 pushed by 0cc4m
51m 10s master
master
51m 10s
CUDA: fix logic for V100 + GGML_CUDA_FORCE_MMQ (#12098) CI #19857: Commit 9c42b17 pushed by JohannesGaessler
36m 47s master
master
36m 47s
ggml: aarch64: implement SVE kernels for q2_k_q8_k vector dot (#12064) CI #19856: Commit 05e6f5a pushed by ggerganov
1h 1m 8s master
master
1h 1m 8s
sync : ggml CI #19855: Pull request #12104 synchronize by ggerganov
15m 53s sync-ggml-25-02-28
sync-ggml-25-02-28
15m 53s
CANN: Fix build error with GCC 13 (#11990) CI #19854: Commit 673cfef pushed by hipudding
1h 7m 56s master
master
1h 7m 56s
vulkan: matmul dequantization improvements (#12015) CI #19853: Commit fbeda90 pushed by 0cc4m
59m 41s master
master
59m 41s
sync : ggml CI #19852: Pull request #12104 opened by ggerganov
18m 17s sync-ggml-25-02-28
sync-ggml-25-02-28
18m 17s
vulkan: improve im2col (#11826) CI #19851: Commit 581650b pushed by 0cc4m
1h 6m 15s master
master
1h 6m 15s
PR: Refine ggml-qnn backend(QNN, Qualcomm Neural Network,aka Qualcomm AI Engine Direct) for latest ggml,whisper.cpp,llama.cpp CI #19850: Pull request #12049 synchronize by jeffzhou2000
37m 46s jeffzhou2000:build_fix
jeffzhou2000:build_fix
37m 46s
Upgrade init_tensor API to return a ggml_status CI #19849: Pull request #11854 synchronize by slaren
50m 6s WilliamTambellini:init_tensor
WilliamTambellini:init_tensor
50m 6s
CUDA: fix logic for V100 + GGML_CUDA_FORCE_MMQ CI #19846: Pull request #12098 opened by JohannesGaessler
36m 0s JohannesGaessler:cuda-fix-v100-force-mmq
JohannesGaessler:cuda-fix-v100-force-mmq
36m 0s
llama : refactor llama_kv_cache, llama_context and llm_build_context CI #19844: Pull request #11213 synchronize by ggerganov
35m 1s gg/llama-kv-cache
gg/llama-kv-cache
35m 1s
llama : refactor llama_kv_cache, llama_context and llm_build_context CI #19843: Pull request #11213 synchronize by ggerganov
5m 36s gg/llama-kv-cache
gg/llama-kv-cache
5m 36s
tool-call: fix Qwen 2.5 Coder support, add micro benchmarks, support trigger patterns for lazy grammars CI #19842: Pull request #12034 synchronize by ochafik
37m 28s ochafik:tool-bench-prod
ochafik:tool-bench-prod
37m 28s
llama : refactor llama_kv_cache, llama_context and llm_build_context CI #19841: Pull request #11213 synchronize by ggerganov
39m 38s gg/llama-kv-cache
gg/llama-kv-cache
39m 38s