mirror of
https://github.com/LostRuins/koboldcpp.git
synced 2026-11-13 17:34:38 +00:00
ab3768cdc2
* memory: refuse rollbacks past the snapshots of the last ubatch The recurrent memory and the DSV4 cache accepted any rollback up to n_rs_seq, whether or not the last ubatch wrote that snapshot. Each now records the deepest rollback its last ubatch guarantees and seq_rm refuses anything past it: - recurrent: n - 1 for a ubatch of n <= n_rs_seq + 1 tokens, 0 for a longer one, which only guarantees the final state - DSV4: min(n, n_rs_seq), the snapshots are rebuilt from the state before the ubatch The dead rollback block of the rollback test becomes the assertion it asked for, and rollback_bound checks the exact bound of each memory after ubatches of 1, 2, n_rs_seq + 1 and n_rs_seq + 2 tokens. * tests: address review from ggerganov Detect architectures with llama_arch_from_string in comp_padding and arch_reserves_single_seq, as in rollback_bound. |
||
|---|---|---|
| .. | ||
| cases-kv.cpp | ||
| cases-rs.cpp | ||
| test-case.cpp | ||
| test-case.h | ||
| test-log.cpp | ||
| test-log.h | ||
| test-runner.cpp | ||
| test-runner.h | ||
| test-util.cpp | ||
| test-util.h | ||