Skip to content

Actions: ggml-org/llama.cpp

Actions

CI

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
build.yml
4,015 workflow run results
4,015 workflow run results

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

ggml-cpu: Fix build with sve (#12059) CI #19782: Commit 393fca6 pushed by MollySophia
1h 48m 12s master
master
1h 48m 12s
vulkan: implement more backpropagation operators (#11914) CI #19781: Commit 61d4f39 pushed by 0cc4m
1h 53m 3s master
master
1h 53m 3s
tool-call: fix Qwen 2.5 Coder support, add micro benchmarks, support trigger patterns for lazy grammars CI #19780: Pull request #12034 synchronize by ochafik
47m 54s ochafik:tool-bench-prod
ochafik:tool-bench-prod
47m 54s
server: support add_generation_prompt query param (#12062) CI #19779: Commit 0b52745 pushed by ochafik
51m 11s master
master
51m 11s
llama : add xcframework build script CI #19778: Pull request #11996 synchronize by danbev
34m 6s danbev:xcframework-build-10747
danbev:xcframework-build-10747
34m 6s
llama : refactor llama_kv_cache, llama_context and llm_build_context CI #19777: Pull request #11213 synchronize by ggerganov
43m 57s gg/llama-kv-cache
gg/llama-kv-cache
43m 57s
llama : refactor llama_kv_cache, llama_context and llm_build_context CI #19776: Pull request #11213 synchronize by ggerganov
4m 22s gg/llama-kv-cache
gg/llama-kv-cache
4m 22s
llama : expose llama_model_n_head_kv in the API (#11997) CI #19775: Commit 3e9a286 pushed by ggerganov
53m 19s master
master
53m 19s
metal : copy kernels for quant to F32/F16 conversions (#12017) CI #19774: Commit 58d07a8 pushed by ggerganov
48m 56s master
master
48m 56s
ggml-cpu: Fix build with sve CI #19773: Pull request #12059 synchronize by MollySophia
32m 52s MollySophia:sve-build
MollySophia:sve-build
32m 52s
ggml: aarch64: implement SVE kernels for q2_k_q8_k vector dot CI #19772: Pull request #12064 opened by Vithulep
36m 7s Vithulep:Q2_k_SVE_Kernel
Vithulep:Q2_k_SVE_Kernel
36m 7s
server: support add_generation_prompt query param CI #19770: Pull request #12062 opened by ochafik
42m 40s ochafik:add_ass_param
ochafik:add_ass_param
42m 40s
PR: Refine ggml-qnn backend(QNN, Qualcomm Neural Network,aka Qualcomm AI Engine Direct) for latest ggml,whisper.cpp,llama.cpp CI #19769: Pull request #12049 synchronize by jeffzhou2000
41m 20s jeffzhou2000:build_fix
jeffzhou2000:build_fix
41m 20s
server: handle echo=false on /v1/completions CI #19768: Pull request #12060 synchronize by rhjdvsgsgks
35m 57s rhjdvsgsgks:patch-4
rhjdvsgsgks:patch-4
35m 57s
server: handle echo=false on /v1/completions CI #19767: Pull request #12060 opened by rhjdvsgsgks
5m 58s rhjdvsgsgks:patch-4
rhjdvsgsgks:patch-4
5m 58s
tool-call: fix Qwen 2.5 Coder support, add micro benchmarks, support trigger patterns for lazy grammars CI #19766: Pull request #12034 synchronize by ochafik
55m 20s ochafik:tool-bench-prod
ochafik:tool-bench-prod
55m 20s
ggml-cpu: Fix build with sve CI #19765: Pull request #12059 opened by MollySophia
37m 56s MollySophia:sve-build
MollySophia:sve-build
37m 56s
PR: Refine ggml-qnn backend(QNN, Qualcomm Neural Network,aka Qualcomm AI Engine Direct) for latest ggml,whisper.cpp,llama.cpp CI #19764: Pull request #12049 synchronize by jeffzhou2000
3h 8m 58s jeffzhou2000:build_fix
jeffzhou2000:build_fix
3h 8m 58s
tool-call: add support for tool-calls using Model Context Protocol CI #19763: Pull request #11556 synchronize by bandoti
38m 48s bandoti:llamacli-tools
bandoti:llamacli-tools
38m 48s
PR: Refine ggml-qnn backend(QNN, Qualcomm Neural Network,aka Qualcomm AI Engine Direct) for latest ggml,whisper.cpp,llama.cpp CI #19762: Pull request #12049 synchronize by jeffzhou2000
18m 17s jeffzhou2000:build_fix
jeffzhou2000:build_fix
18m 17s
Vulkan: add OP sigmoid CI #19761: Pull request #12056 opened by foldl
32m 40s foldl:vulkan_add_sigmoid
foldl:vulkan_add_sigmoid
32m 40s
PR: Refine ggml-qnn backend(QNN, Qualcomm Neural Network,aka Qualcomm AI Engine Direct) for latest ggml,whisper.cpp,llama.cpp CI #19760: Pull request #12049 synchronize by jeffzhou2000
35m 37s jeffzhou2000:build_fix
jeffzhou2000:build_fix
35m 37s
PR: Refine ggml-qnn backend(QNN, Qualcomm Neural Network,aka Qualcomm AI Engine Direct) for latest ggml,whisper.cpp,llama.cpp CI #19759: Pull request #12049 synchronize by jeffzhou2000
35m 42s jeffzhou2000:build_fix
jeffzhou2000:build_fix
35m 42s
tool-call: add support for tool-calls using Model Context Protocol CI #19758: Pull request #11556 synchronize by bandoti
32m 31s bandoti:llamacli-tools
bandoti:llamacli-tools
32m 31s
opencl: fix for small models (#11950) CI #19757: Commit 34a846b pushed by max-krasnyansky
43m 20s master
master
43m 20s