df9b610c7f
score_memories() drops each memory from the context one at a time, runs prompt_logprobs against the full conversation, and builds a divergence matrix: memories × responses. Row sums = memory importance (for graph weight updates) Column sums = response memory-dependence (training candidates) Uses vLLM's prompt_logprobs to check "would the model have said this without this memory?" — one forward pass per memory, all responses scored at once. ~3s per memory on B200. Co-Authored-By: Proof of Concept <poc@bcachefs.org> |
||
|---|---|---|
| .. | ||
| bash.rs | ||
| context.rs | ||
| edit.rs | ||
| glob_tool.rs | ||
| grep.rs | ||
| memory.rs | ||
| mod.rs | ||
| read.rs | ||
| training.rs | ||
| write.rs | ||