Skip to content

Actions: ggml-org/llama.cpp

Actions

All workflows

Actions

Loading...
Loading

Showing runs from all workflows
14,977 workflow run results
14,977 workflow run results

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

server : set default top-k to 1 in the web ui EditorConfig Checker #20009: Pull request #10935 opened by ggerganov
1m 51s gg/webui-topk-1
gg/webui-topk-1
1m 51s
server : set default top-k to 1 in the web ui Pull Request Labeler #6546: Pull request #10935 opened by ggerganov
49s
49s
rpc-server : add support for the SYCL backend CI #17858: Pull request #10934 opened by rgerganov
19m 52s rgerganov:rpc-sycl
rgerganov:rpc-sycl
19m 52s
rpc-server : add support for the SYCL backend EditorConfig Checker #20008: Pull request #10934 opened by rgerganov
20s rgerganov:rpc-sycl
rgerganov:rpc-sycl
20s
rpc-server : add support for the SYCL backend Server #9276: Pull request #10934 opened by rgerganov
5m 42s rgerganov:rpc-sycl
rgerganov:rpc-sycl
5m 42s
rpc-server : add support for the SYCL backend Pull Request Labeler #6545: Pull request #10934 opened by rgerganov
14s
14s
llama : the WPM vocabs use the CLS token as BOS Server #9275: Pull request #10930 opened by ggerganov
4m 53s gg/wpm-fix-bos
gg/wpm-fix-bos
4m 53s
llama : the WPM vocabs use the CLS token as BOS EditorConfig Checker #20007: Pull request #10930 opened by ggerganov
20s gg/wpm-fix-bos
gg/wpm-fix-bos
20s
llama : the WPM vocabs use the CLS token as BOS CI #17857: Pull request #10930 opened by ggerganov
31m 19s gg/wpm-fix-bos
gg/wpm-fix-bos
31m 19s
llama : the WPM vocabs use the CLS token as BOS Pull Request Labeler #6544: Pull request #10930 opened by ggerganov
17s
17s
convert : add BertForMaskedLM (#10919) Python Type-Check #1317: Commit 5cd85b5 pushed by ggerganov
1m 21s master
master
1m 21s
convert : add BertForMaskedLM (#10919) Python check requirements.txt #2420: Commit 5cd85b5 pushed by ggerganov
2m 27s master
master
2m 27s
convert : add BertForMaskedLM (#10919) flake8 Lint #16987: Commit 5cd85b5 pushed by ggerganov
23s master
master
23s
convert : add BertForMaskedLM (#10919) EditorConfig Checker #20006: Commit 5cd85b5 pushed by ggerganov
21s master
master
21s
Allow user to compile with any cuda version using github actions Pull Request Labeler #6543: Pull request #10928 opened by jianlins
18s
18s
vulkan: optimize coopmat2 dequant functions (#10855) EditorConfig Checker #20004: Commit a91a413 pushed by 0cc4m
21s master
master
21s
vulkan: build fixes for 32b Server #9274: Pull request #10927 opened by jeffbolznv
6m 14s jeffbolznv:ggml_vk_host_get_build_fix
jeffbolznv:ggml_vk_host_get_build_fix
6m 14s
vulkan: build fixes for 32b Pull Request Labeler #6542: Pull request #10927 opened by jeffbolznv
15s
15s
vulkan: build fixes for 32b EditorConfig Checker #20003: Pull request #10927 opened by jeffbolznv
18s jeffbolznv:ggml_vk_host_get_build_fix
jeffbolznv:ggml_vk_host_get_build_fix
18s
vulkan: build fixes for 32b CI #17856: Pull request #10927 opened by jeffbolznv
24m 55s jeffbolznv:ggml_vk_host_get_build_fix
jeffbolznv:ggml_vk_host_get_build_fix
24m 55s
Publish Docker image Publish Docker image #14788: Scheduled
31m 59s master
master
31m 59s
Close inactive issues Close inactive issues #280: Scheduled
25s master
master
25s
ggml-cpu: replace NEON asm with intrinsics in ggml_gemv_q4_0_4x8_q8_0… Server #9273: Commit e34c5af pushed by slaren
6m 7s master
master
6m 7s
ggml-cpu: replace NEON asm with intrinsics in ggml_gemv_q4_0_4x8_q8_0… EditorConfig Checker #20002: Commit e34c5af pushed by slaren
20s master
master
20s
ggml-cpu: replace NEON asm with intrinsics in ggml_gemv_q4_0_4x8_q8_0… CI #17855: Commit e34c5af pushed by slaren
38m 9s master
master
38m 9s
ProTip! You can narrow down the results and go further in time using created:<2024-12-20 or the other filters available.