Actions: ggml-org/llama.cpp
Actions
9,208 workflow run results
9,208 workflow run results
tool-call: Qwen3 Coder chat format support
CI
#25878:
Pull request #15162
synchronize
by
ochafik
tool-call: Qwen3 Coder chat format support
CI
#25877:
Pull request #15162
synchronize
by
ochafik
tool-call: Qwen3 Coder chat format support
CI
#25876:
Pull request #15162
synchronize
by
ochafik
tool-call: Qwen3 Coder chat format support
CI
#25875:
Pull request #15162
synchronize
by
ochafik
tool-call: Qwen3 Coder chat format support
CI
#25874:
Pull request #15162
synchronize
by
ochafik
soft_max (attn sinks)
CI
#25859:
Pull request #15152
opened
by
lhez
reduce_rows_f32 kernel, leading up to 25x perf improvement on kernel-level and 10% perf increase for Gemma3n
CI
#25856:
Pull request #15132
synchronize
by
ORippler