Skip to content

Actions: ggml-org/llama.cpp

Actions

Check Pre-Tokenizer Hashes

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
pre-tokenizer-hashes.yml
417 workflow run results
417 workflow run results

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

metal : make the backend async (wip) Check Pre-Tokenizer Hashes #285: Commit 84ae836 pushed by ggerganov
54m 55s gg/metal-async
gg/metal-async
54m 55s
Feat: Apertus model implementation Check Pre-Tokenizer Hashes #284: Pull request #15852 synchronize by pwilkin
57m 1s pwilkin:apertus-implementation
pwilkin:apertus-implementation
57m 1s
Feat: Apertus model implementation Check Pre-Tokenizer Hashes #283: Pull request #15852 synchronize by pwilkin
34m 42s pwilkin:apertus-implementation
pwilkin:apertus-implementation
34m 42s
metal : simplify FA pipeline creation functions Check Pre-Tokenizer Hashes #282: Commit d034c5d pushed by ggerganov
15m 28s gg/metal-refactor
gg/metal-refactor
15m 28s
convert : force setting sliding_window from original config (#15867) Check Pre-Tokenizer Hashes #281: Commit 233d773 pushed by danbev
2m 30s master
master
2m 30s
convert : force setting sliding_window from original config Check Pre-Tokenizer Hashes #280: Pull request #15867 synchronize by danbev
49s danbev:embeddinggemma-sliding-window-conversion
danbev:embeddinggemma-sliding-window-conversion
49s
convert : force setting sliding_window from original config Check Pre-Tokenizer Hashes #279: Pull request #15867 opened by danbev
2m 21s danbev:embeddinggemma-sliding-window-conversion
danbev:embeddinggemma-sliding-window-conversion
2m 21s
cont : add comments Check Pre-Tokenizer Hashes #278: Commit 3dec397 pushed by ggerganov
33s gg/model-avoid-cont3d
gg/model-avoid-cont3d
33s
Feat: Apertus model implementation Check Pre-Tokenizer Hashes #277: Pull request #15852 opened by pwilkin
29s pwilkin:apertus-implementation
pwilkin:apertus-implementation
29s
Add support for Qwen3-Reranker Check Pre-Tokenizer Hashes #276: Pull request #15824 opened by iamlemec
11m 9s iamlemec:qwen3-rerank
iamlemec:qwen3-rerank
11m 9s
convert : use reflinks for faster conversion Check Pre-Tokenizer Hashes #275: Pull request #15727 synchronize by compilade
4m 7s compilade/convert-reflinks
compilade/convert-reflinks
4m 7s
gguf-py : allow previewing reflinked size on non-Linux platforms Check Pre-Tokenizer Hashes #274: Commit 810039c pushed by compilade
55m 17s compilade/convert-reflinks
compilade/convert-reflinks
55m 17s
convert : use reflinks for faster conversion Check Pre-Tokenizer Hashes #273: Pull request #15727 synchronize by compilade
34s compilade/convert-reflinks
compilade/convert-reflinks
34s
convert : remove unused field ModelTensorInfo.src_qtype Check Pre-Tokenizer Hashes #272: Commit add6b48 pushed by compilade
34s compilade/convert-reflinks
compilade/convert-reflinks
34s
convert : use reflinks for faster conversion Check Pre-Tokenizer Hashes #271: Pull request #15727 synchronize by compilade
4m 58s compilade/convert-reflinks
compilade/convert-reflinks
4m 58s
convert : more robust default ftype detection Check Pre-Tokenizer Hashes #270: Commit 1f18f68 pushed by compilade
16m 26s compilade/convert-reflinks
compilade/convert-reflinks
16m 26s
convert : use reflinks for faster conversion Check Pre-Tokenizer Hashes #269: Pull request #15727 synchronize by compilade
35s compilade/convert-reflinks
compilade/convert-reflinks
35s
convert : use reflinks for faster conversion Check Pre-Tokenizer Hashes #268: Pull request #15727 synchronize by compilade
23m 37s compilade/convert-reflinks
compilade/convert-reflinks
23m 37s
convert : allow sharding reflinked models Check Pre-Tokenizer Hashes #267: Commit eecb83c pushed by compilade
1m 51s compilade/convert-reflinks
compilade/convert-reflinks
1m 51s
Implement --log-colors with always/never/auto Check Pre-Tokenizer Hashes #266: Commit f06c91b pushed by ericcurtin
50m 1s auto-color
auto-color
50m 1s
llama : add support for EmbeddingGemma 300m (#15798) Check Pre-Tokenizer Hashes #265: Commit fb15d64 pushed by danbev
1h 5m 44s master
master
1h 5m 44s
llama : add support for EmbeddingGemma 300m Check Pre-Tokenizer Hashes #264: Pull request #15798 opened by danbev
50m 54s danbev:embeddinggemma
danbev:embeddinggemma
50m 54s
model : add grok-2 support Check Pre-Tokenizer Hashes #263: Pull request #15539 synchronize by CISC
21m 6s cisc/grok-2
cisc/grok-2
21m 6s
model : add grok-2 support Check Pre-Tokenizer Hashes #262: Pull request #15539 synchronize by CISC
47m 19s cisc/grok-2
cisc/grok-2
47m 19s
Merge branch 'master' into cisc/grok-2 Check Pre-Tokenizer Hashes #261: Commit c0d755c pushed by CISC
46m 7s cisc/grok-2
cisc/grok-2
46m 7s