Get up and running with Kimi, GLM, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.
kvcache: Sliding window cache only needs a single batch total
Jesse Gross1feff6197791
diff --git a/kvcache/causal.go b/kvcache/causal.goindex aacaf540f..fb4f0f743 100644--- a/kvcache/causal.go+++ b/kvcache/causal.go@@ -119,10 +119,10 @@ func (c *Causal) Init(backend ml.Backend, dtype ml.DType, maxSequences, capacity}var cacheSize int- if c.windowSize == math.MaxInt32 || capacity < int(c.windowSize)+maxBatch {+ if c.windowSize == math.MaxInt32 || capacity < int(c.windowSize) {cacheSize = maxSequences * capacity} else {- cacheSize = maxSequences * (int(c.windowSize) + maxBatch)+ cacheSize = (maxSequences * int(c.windowSize)) + maxBatch}cacheSize = roundUp(cacheSize, c.config.CachePadding)c.cells = make([]cacheCell, cacheSize)