Skip to content

Actions: Distillative-AI/llama.cpp

Actions

Check Pre-Tokenizer Hashes

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
pre-tokenizer-hashes.yml
17 workflow runs
17 workflow runs

Filter by Event

⌥ + click/return to exclude

Filter by Status

⌥ + click/return to exclude

Filter by Branch

⌥ + click/return to exclude

Filter by Actor

⌥ + click/return to exclude
cuda: fuse MoE weighted expert reduction (#25952) Check Pre-Tokenizer Hashes #17: Commit 3466812 pushed by AsherBond
1d 0h 0m 2s master
master
1d 0h 0m 2s
ci : allow make-release to target a specific commit (#27234) Check Pre-Tokenizer Hashes #16: Commit 7c35571 pushed by AsherBond
1d 0h 0m 2s master
master
1d 0h 0m 2s
sync : ggml Check Pre-Tokenizer Hashes #15: Commit 9b05354 pushed by AsherBond
1d 0h 0m 1s master
master
1d 0h 0m 1s
metal : add SILU_BACK (#25982) Check Pre-Tokenizer Hashes #14: Commit 221f0f6 pushed by AsherBond
1d 0h 0m 1s master
master
1d 0h 0m 1s
ui: Prioritize favorite models in model selection (#24766) Check Pre-Tokenizer Hashes #13: Commit 9c0ac88 pushed by AsherBond
1d 0h 0m 2s master
master
1d 0h 0m 2s
chat : fix LFM2 tool-call parsing double-escaping (#24667) Check Pre-Tokenizer Hashes #12: Commit 7dad2f1 pushed by AsherBond
1d 0h 0m 1s master
master
1d 0h 0m 1s
mtmd: fix Gemma 4 unified FPE (#24088) Check Pre-Tokenizer Hashes #11: Commit 94a220c pushed by AsherBond
1d 0h 0m 1s master
master
1d 0h 0m 1s
metal : fix event synchronization (#22260) Check Pre-Tokenizer Hashes #10: Commit 8635e22 pushed by AsherBond
2m 56s master
master
2m 56s
mtmd: also support LLAMA_ROPE_TYPE_NONE (#22242) Check Pre-Tokenizer Hashes #9: Commit 82d3f4d pushed by AsherBond
4m 48s master
master
4m 48s
mtmd: add pos_0 to mtmd_image_tokens_get_decoder_pos (breaking change… Check Pre-Tokenizer Hashes #8: Commit 1912407 pushed by AsherBond
10m 7s master
master
10m 7s
android : libcommon -> libllama-common (#22076) Check Pre-Tokenizer Hashes #7: Commit 23b8cc4 pushed by AsherBond
1m 7s master
master
1m 7s
codeowners: add team member comments (#21714) Check Pre-Tokenizer Hashes #6: Commit b572d1e pushed by AsherBond
2m 37s master
master
2m 37s
llama : re-enable manual LoRA adapter free (#19983) Check Pre-Tokenizer Hashes #5: Commit 312cf03 pushed by AsherBond
6m 11s master
master
6m 11s
ggml: add GATED_DELTA_NET op (#19504) Check Pre-Tokenizer Hashes #4: Commit c5a7788 pushed by AsherBond
12m 42s master
master
12m 42s
ggml-cpu: optimise s390x multiply extend instructions (#20032) Check Pre-Tokenizer Hashes #3: Commit 2afcdb9 pushed by AsherBond
1m 42s master
master
1m 42s
Improve CUDA graph capture (#19754) Check Pre-Tokenizer Hashes #2: Commit a0c91e8 pushed by AsherBond
57s master
master
57s
perplexity: add proper batching (#19661) Check Pre-Tokenizer Hashes #1: Commit d612901 pushed by AsherBond
1m 19s master
master
1m 19s