Skip to content

Actions: ggml-org/llama.cpp

Actions

CI

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
build.yml
2,683 workflow run results
2,683 workflow run results

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

lora : update API names CI #18198: Pull request #11167 synchronize by ggerganov
37m 4s gg/llama-adapter-naming
gg/llama-adapter-naming
37m 4s
lora : update API names CI #18197: Pull request #11167 synchronize by ggerganov
5m 53s gg/llama-adapter-naming
gg/llama-adapter-naming
5m 53s
lora : update API names CI #18196: Pull request #11167 opened by ggerganov
1m 16s gg/llama-adapter-naming
gg/llama-adapter-naming
1m 16s
vulkan: support copy from f32 to q4_0/q4_1/q5_0/q5_1/q8_0/iq4_nl CI #18195: Pull request #11166 opened by jeffbolznv
38m 4s jeffbolznv:copy-to-quant
jeffbolznv:copy-to-quant
38m 4s
llama : add llama_vocab, functions -> methods, naming CI #18194: Pull request #11110 synchronize by ggerganov
29m 49s gg/llama-refactor-7
gg/llama-refactor-7
29m 49s
vocab : more pimpl CI #18193: Pull request #11165 opened by ggerganov
31m 6s gg/llama-refactor-10
gg/llama-refactor-10
31m 6s
hparams : move vocab params to llama_vocab CI #18192: Pull request #11159 synchronize by ggerganov
22m 35s gg/llama-refactor-9
gg/llama-refactor-9
22m 35s
llama : add struct llama_vocab to the API CI #18191: Pull request #11156 synchronize by ggerganov
23m 29s gg/llama-refactor-8
gg/llama-refactor-8
23m 29s
vocab : minor tokenization optimizations CI #18190: Pull request #11160 synchronize by ggerganov
36m 20s gg/llama-tokenizer-opt
gg/llama-tokenizer-opt
36m 20s
Vulkan: Fix float16 use on devices without float16 support + fix subgroup_size_control validation error CI #18189: Pull request #11161 opened by 0cc4m
46m 15s 0cc4m/vulkan-fix-float16-validation
0cc4m/vulkan-fix-float16-validation
46m 15s
vocab : minor tokenization optimizations CI #18188: Pull request #11160 opened by ggerganov
24m 49s gg/llama-tokenizer-opt
gg/llama-tokenizer-opt
24m 49s
hparams : move vocab params to llama_vocab CI #18187: Pull request #11159 opened by ggerganov
41m 18s gg/llama-refactor-9
gg/llama-refactor-9
41m 18s
SYCL: Refactor ggml_sycl_compute_forward CI #18186: Pull request #11121 synchronize by qnixsynapse
32m 35s qnixsynapse:cf_refactor
qnixsynapse:cf_refactor
32m 35s
llama : add struct llama_vocab to the API CI #18185: Pull request #11156 synchronize by ggerganov
33m 5s gg/llama-refactor-8
gg/llama-refactor-8
33m 5s
llama : add struct llama_vocab to the API CI #18184: Pull request #11156 opened by ggerganov
24m 48s gg/llama-refactor-8
gg/llama-refactor-8
24m 48s
CUDA Graph Compute Function Refactor (precursor for performance improvements) CI #18183: Pull request #11042 synchronize by aendk
31m 6s aendk:akieslinger/refactor_cuda_backend
aendk:akieslinger/refactor_cuda_backend
31m 6s
llama : add llama_vocab, functions -> methods, naming CI #18182: Pull request #11110 synchronize by ggerganov
33m 49s gg/llama-refactor-7
gg/llama-refactor-7
33m 49s
model: Add support for PhiMoE arch (#11003) CI #18181: Commit f8feb4b pushed by phymbert
36m 52s master
master
36m 52s
model: Add support for PhiMoE arch CI #18180: Pull request #11003 synchronize by ggerganov
28m 50s phymbert/model/phi35-moe
phymbert/model/phi35-moe
28m 50s
model: Add support for PhiMoE arch CI #18179: Pull request #11003 synchronize by ggerganov
4m 15s phymbert/model/phi35-moe
phymbert/model/phi35-moe
4m 15s
llama-chat : add phi 4 template (#11148) CI #18178: Commit d9feae1 pushed by ngxson
44m 51s master
master
44m 51s
SYCL: Refactor ggml_sycl_compute_forward CI #18177: Pull request #11121 synchronize by qnixsynapse
50m 3s qnixsynapse:cf_refactor
qnixsynapse:cf_refactor
50m 3s
Refactor llama-run to split out opt struct CI #18176: Pull request #11151 synchronize by ericcurtin
20m 25s opt-class
opt-class
20m 25s
Refactor llama-run to split out opt struct CI #18175: Pull request #11151 synchronize by ericcurtin
58m 45s opt-class
opt-class
58m 45s
Refactor llama-run to split out opt struct CI #18174: Pull request #11151 opened by ericcurtin
6m 42s opt-class
opt-class
6m 42s