Skip to content

Actions: ggml-org/llama.cpp

Actions

CI

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
build.yml
7,068 workflow run results
7,068 workflow run results

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

metal: optimize matrix multiplication kernel CI #23249: Pull request #13941 opened by mikek498
53m 2s mikek498:metal-mat-mul
mikek498:metal-mat-mul
53m 2s
SYCL: Implement few same quantized type copy kernels CI #23248: Pull request #13739 synchronize by qnixsynapse
1h 30m 36s sycl/same_q_cpy
sycl/same_q_cpy
1h 30m 36s
llama : support multiple classifier outputs and labels CI #23247: Pull request #13940 opened by CISC
1h 42m 33s cisc/multiple-classifier-outputs
cisc/multiple-classifier-outputs
1h 42m 33s
kv-cache : refactor + add llama_memory_state_i CI #23246: Pull request #13746 synchronize by ggerganov
1h 12m 4s gg/kv-cache-simplify-part3
gg/kv-cache-simplify-part3
1h 12m 4s
CUDA: add a prop in ggml_cuda_device_infor for distinguish iGPU or dG… CI #23245: Commit eb39499 pushed by JohannesGaessler
42m 57s master
master
42m 57s
opencl: add backend_synchronize CI #23244: Pull request #13939 opened by lhez
52m 0s CodeLinaro:backend-sync-new
CodeLinaro:backend-sync-new
52m 0s
vulkan: fix warnings in perf logger querypool code CI #23243: Pull request #13937 opened by jeffbolznv
50m 8s jeffbolznv:querypool_warnings
jeffbolznv:querypool_warnings
50m 8s
vulkan: automatically deduce size of push constants CI #23242: Pull request #13936 opened by jeffbolznv
53m 16s jeffbolznv:pc_size_mismatch
jeffbolznv:pc_size_mismatch
53m 16s
server: update deepseek reasoning format (pass reasoning_content as diffs) CI #23241: Pull request #13933 synchronize by ochafik
48m 26s ochafik:fix-reasoning-diffs
ochafik:fix-reasoning-diffs
48m 26s
server: update deepseek reasoning format (pass reasoning_content as diffs) CI #23240: Pull request #13933 synchronize by ochafik
3m 39s ochafik:fix-reasoning-diffs
ochafik:fix-reasoning-diffs
3m 39s
chat: improve llama 3.x handling of <|python_tag|> (+ allow --special combo) CI #23239: Pull request #13932 synchronize by ochafik
48m 27s ochafik:fix-python-tag
ochafik:fix-python-tag
48m 27s
threading: support for GGML_SCHED_PRIO_LOW, update thread info on Windows to avoid throttling CI #23237: Pull request #12995 synchronize by max-krasnyansky
59m 56s maxk/sched-prio-updates
maxk/sched-prio-updates
59m 56s
chat: improve llama 3.x handling of <|python_tag|> (+ allow --special combo) CI #23235: Pull request #13932 synchronize by ochafik
1h 1m 0s ochafik:fix-python-tag
ochafik:fix-python-tag
1h 1m 0s
server: update deepseek reasoning format (pass reasoning_content as diffs) CI #23234: Pull request #13933 synchronize by ochafik
49m 32s ochafik:fix-reasoning-diffs
ochafik:fix-reasoning-diffs
49m 32s
server: update deepseek reasoning format (pass reasoning_content as diffs) CI #23232: Pull request #13933 opened by ochafik
11m 45s ochafik:fix-reasoning-diffs
ochafik:fix-reasoning-diffs
11m 45s
chat: improve llama 3.x handling of <|python_tag|> (+ allow --special combo) CI #23230: Pull request #13932 opened by ochafik
49m 9s ochafik:fix-python-tag
ochafik:fix-python-tag
49m 9s
chat: allow unclosed thinking tags CI #23229: Pull request #13931 opened by ochafik
46m 41s ochafik:allow-unclosed-think
ochafik:allow-unclosed-think
46m 41s
ggml-cpu : split arch-specific implementations CI #23222: Pull request #13892 synchronize by xctan
1h 0m 25s xctan:split-arch
xctan:split-arch
1h 0m 25s
ggml-cpu : split arch-specific implementations CI #23221: Pull request #13892 synchronize by xctan
2m 43s xctan:split-arch
xctan:split-arch
2m 43s
CUDA: fix typo in FlashAttention code (#13926) CI #23220: Commit e562eec pushed by JohannesGaessler
50m 45s master
master
50m 45s
ggml-cpu : split arch-specific implementations CI #23218: Pull request #13892 synchronize by xctan
1h 49m 32s xctan:split-arch
xctan:split-arch
1h 49m 32s
sched : avoid changing cur_copy when a graph is already allocated (#1… CI #23216: Commit b47ab7b pushed by slaren
2h 39m 44s master
master
2h 39m 44s
Granite Four CI #23215: Pull request #13550 synchronize by gabe-l-hart
2h 16m 12s gabe-l-hart:GraniteFour
gabe-l-hart:GraniteFour
2h 16m 12s
parallel : increase the variability of the prompt lengths (#13927) CI #23212: Commit dd665cc pushed by ggerganov
2h 40m 54s master
master
2h 40m 54s
parallel : increase the variability of the prompt lengths CI #23211: Pull request #13927 opened by ggerganov
2h 49m 2s gg/parallel-junk-rand
gg/parallel-junk-rand
2h 49m 2s