Skip to content

Actions: ggml-org/llama.cpp

Actions

CI

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
build.yml
2,445 workflow run results
2,445 workflow run results

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

llama : remove check flash_attn with lora CI #18103: Pull request #11104 opened by ngxson
1h 23m 57s ngxson:xsn/flash_attn_lora
ngxson:xsn/flash_attn_lora
1h 23m 57s
llama : prevent system info string accumulation across calls (#11101) CI #18102: Commit 96a1dc2 pushed by ggerganov
1h 44m 2s master
master
1h 44m 2s
feat(ci): add visionOS build workflow CI #18101: Pull request #11103 opened by ggerganov
1h 17m 38s shards-lang/gio/visionos-ci
shards-lang/gio/visionos-ci
1h 17m 38s
fix(log): prevent system info string accumulation across calls in llama_print_system_info() CI #18100: Pull request #11101 opened by a-ghorbani
2h 17m 20s a-ghorbani:fix-system-info-string-accumulation
a-ghorbani:fix-system-info-string-accumulation
2h 17m 20s
llama : rename missed batch params/vars to ubatch (#10059) CI #18099: Commit 6369f86 pushed by ggerganov
3h 24m 22s master
master
3h 24m 22s
llama : remove notion of CLS token CI #18098: Pull request #11064 synchronize by ggerganov
2h 46m 38s gg/llama-refactor-5
gg/llama-refactor-5
2h 46m 38s
llama : update llama_model API names (#11063) CI #18097: Commit 47182dd pushed by ggerganov
3h 55m 24s master
master
3h 55m 24s
tokenize : escape the prompt (#11058) CI #18096: Commit 3e6e7a6 pushed by ggerganov
3h 28m 36s master
master
3h 28m 36s
tokenize : escape the prompt CI #18095: Pull request #11058 synchronize by ggerganov
1h 57m 14s gg/tokenize-escape
gg/tokenize-escape
1h 57m 14s
mmap : fix fileno macro clash (#11076) CI #18094: Commit ae2f606 pushed by ggerganov
3h 11m 1s master
master
3h 11m 1s
llama : use LLAMA_TOKEN_NULL (#11062) CI #18093: Commit 727368c pushed by ggerganov
3h 9m 18s master
master
3h 9m 18s
llama : use _impl suffix instead of _internal (#11060) CI #18092: Commit 5047dd3 pushed by ggerganov
3h 9m 30s master
master
3h 9m 30s
fix: Vulkan shader gen binary path when Cross-compiling CI #18090: Pull request #11096 synchronize by ag2s20150909
48m 15s patch-2
patch-2
48m 15s
fix: Vulkan shader gen binary path when Cross-compiling CI #18089: Pull request #11096 synchronize by ag2s20150909
7m 58s patch-2
patch-2
7m 58s
fix: Vulkan shader gen binary path when Cross-compiling CI #18088: Pull request #11096 opened by ag2s20150909
7m 46s patch-2
patch-2
7m 46s
CUDA: add BF16 support (#11093) CI #18087: Commit 46e3556 pushed by JohannesGaessler
45m 28s master
master
45m 28s
llama-run : fix context size CI #18086: Pull request #11094 opened by ericcurtin
20m 28s ericcurtin:context-size-llama-run
ericcurtin:context-size-llama-run
20m 28s
CUDA: add BF16 support CI #18085: Pull request #11093 synchronize by JohannesGaessler
34m 52s JohannesGaessler:cuda-bf16-3
JohannesGaessler:cuda-bf16-3
34m 52s
CUDA: add BF16 support CI #18084: Pull request #11093 synchronize by JohannesGaessler
3m 49s JohannesGaessler:cuda-bf16-3
JohannesGaessler:cuda-bf16-3
3m 49s
CUDA: add BF16 support CI #18083: Pull request #11093 synchronize by JohannesGaessler
3m 29s JohannesGaessler:cuda-bf16-3
JohannesGaessler:cuda-bf16-3
3m 29s
CUDA: add BF16 support CI #18082: Pull request #11093 opened by JohannesGaessler
14m 14s JohannesGaessler:cuda-bf16-3
JohannesGaessler:cuda-bf16-3
14m 14s
[SYCL] Fix build on Windows when ccache enabled (#9954) CI #18081: Pull request #9976 synchronize by MakeDecisionWorth
23m 8s MakeDecisionWorth:patch-3
MakeDecisionWorth:patch-3
23m 8s
SYCL: Use get_multi_ptr instead of deprecated get_pointer in wkv6 CI #18080: Pull request #11087 opened by qnixsynapse
22m 28s qnixsynapse:multi_pointer
qnixsynapse:multi_pointer
22m 28s
llama : rename missed batch params/vars to ubatch CI #18079: Pull request #10059 synchronize by danbev
24m 20s danbev:ubatch-leftovers
danbev:ubatch-leftovers
24m 20s
vulkan: scale caching for k quants + misc fixes CI #18078: Pull request #11081 synchronize by netrunnereve
19m 28s vulkan
vulkan
19m 28s