Skip to content

fix: return ContextLengthExceeded when prompt exceeds effective KV cache size#7815

Merged
DOsinga merged 1 commit into
mainfrom
fix/local-inference-kv-cache-context-overflow
Mar 11, 2026
Merged

fix: return ContextLengthExceeded when prompt exceeds effective KV cache size#7815
DOsinga merged 1 commit into
mainfrom
fix/local-inference-kv-cache-context-overflow

Commits

Commits on Mar 11, 2026