Skip to content

Actions: CISC/llama.cpp

Actions

All workflows

Actions

Loading...
Loading

Showing runs from all workflows
351 workflow run results
351 workflow run results

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

metal : improve FA + improve MoE (#12612) Python Type-Check #50: Commit b4ae508 pushed by CISC
1m 12s qwen2moe-cb-fix
qwen2moe-cb-fix
1m 12s
use existing hparams if passed Python Type-Check #49: Commit 0682b46 pushed by CISC
1m 19s fix-model-hparams-init
fix-model-hparams-init
1m 19s
use existing hparams if passed Python check requirements.txt #59: Commit 0682b46 pushed by CISC
2m 43s fix-model-hparams-init
fix-model-hparams-init
2m 43s
set positional args correctly Python check requirements.txt #58: Commit a3e791f pushed by CISC
2m 42s fix-model-hparams-init
fix-model-hparams-init
2m 42s
set positional args correctly Python Type-Check #48: Commit a3e791f pushed by CISC
1m 15s fix-model-hparams-init
fix-model-hparams-init
1m 15s
Fix Mistral3/Gemma3 model hparams init Python Type-Check #47: Commit e39e0b8 pushed by CISC
1m 9s fix-model-hparams-init
fix-model-hparams-init
1m 9s
Fix Mistral3/Gemma3 model hparams init Python check requirements.txt #57: Commit e39e0b8 pushed by CISC
3m 13s fix-model-hparams-init
fix-model-hparams-init
3m 13s
ggml-cpu : update KleidiAI to v1.5.0 (#12568) Python check requirements.txt #56: Commit 053b3f9 pushed by CISC
2m 45s fix-model-hparams-init
fix-model-hparams-init
2m 45s
ggml-cpu : update KleidiAI to v1.5.0 (#12568) Python Type-Check #46: Commit 053b3f9 pushed by CISC
1m 25s fix-model-hparams-init
fix-model-hparams-init
1m 25s
Support Qwen3 Python Type-Check #45: Commit 5deee92 pushed by CISC
1m 21s qwen3
qwen3
1m 21s
Support Qwen3 Python check requirements.txt #55: Commit 5deee92 pushed by CISC
2m 54s qwen3
qwen3
2m 54s
qwen3 arch Python Type-Check #44: Commit 420eb3f pushed by CISC
1m 10s qwen3
qwen3
1m 10s
model : do not repack if a GPU device is present (#12498) Python Type-Check #43: Commit af04481 pushed by CISC
1m 15s qwen3
qwen3
1m 15s
model : do not repack if a GPU device is present (#12498) Python check requirements.txt #54: Commit af04481 pushed by CISC
2m 49s qwen3
qwen3
2m 49s
[SYCL] Fix build on Windows when ccache enabled (#9954) (#9976) Python check requirements.txt #53: Commit 1aa87ee pushed by CISC
2m 46s llama_model_loader_tensor_cleanup
llama_model_loader_tensor_cleanup
2m 46s
[SYCL] Fix build on Windows when ccache enabled (#9954) (#9976) Python Type-Check #42: Commit 1aa87ee pushed by CISC
1m 25s llama_model_loader_tensor_cleanup
llama_model_loader_tensor_cleanup
1m 25s
convert : avoid calls to tokenizer.added_tokens_decoder (#12473) Python check requirements.txt #52: Commit 732b5fb pushed by CISC
2m 45s qwen2moe_optional_qkv_bias
qwen2moe_optional_qkv_bias
2m 45s
convert : avoid calls to tokenizer.added_tokens_decoder (#12473) Python Type-Check #41: Commit 732b5fb pushed by CISC
1m 9s qwen2moe_optional_qkv_bias
qwen2moe_optional_qkv_bias
1m 9s
Support chat_template.json Python Type-Check #40: Commit d1e1ec5 pushed by CISC
1m 8s convert-chat-template-json
convert-chat-template-json
1m 8s
opencl: improve profiling (#12442) Python Type-Check #39: Commit d84635b pushed by CISC
1m 15s convert-chat-template-json
convert-chat-template-json
1m 15s
opencl: improve profiling (#12442) Python check requirements.txt #51: Commit d84635b pushed by CISC
2m 40s convert-chat-template-json
convert-chat-template-json
2m 40s
fatfingers-- Python Type-Check #38: Commit 1b2a53a pushed by CISC
1m 27s tied-word-embeddings
tied-word-embeddings
1m 27s
fatfingers-- Python check requirements.txt #50: Commit 1b2a53a pushed by CISC
2m 39s tied-word-embeddings
tied-word-embeddings
2m 39s
check++ Python Type-Check #37: Commit 0cc8cb5 pushed by CISC
1m 23s tied-word-embeddings
tied-word-embeddings
1m 23s
check++ Python check requirements.txt #49: Commit 0cc8cb5 pushed by CISC
2m 40s tied-word-embeddings
tied-word-embeddings
2m 40s