(self, seq_id: int, keep_len: int)
| 2379 | self.ready_pos[seq_id] = self.verify_h_pos[seq_id][row] + 1 |
| 2380 | |
| 2381 | def _truncate_memory(self, seq_id: int, keep_len: int) -> None: |
| 2382 | if seq_id < 0 or seq_id >= self.n_seq_max: |
| 2383 | return |
| 2384 | if self.is_mem_shared: |
| 2385 | self.context_pos[seq_id] = min(self.context_pos[seq_id], keep_len) |
| 2386 | return |
| 2387 | if not llama_cpp.llama_memory_seq_rm( |
| 2388 | self.mem, |
| 2389 | seq_id, |
| 2390 | keep_len, |
| 2391 | -1, |
| 2392 | ): |
| 2393 | raise RuntimeError( |
| 2394 | f"failed to truncate MTP draft sequence {seq_id} at position {keep_len}" |
| 2395 | ) |
| 2396 | self.context_pos[seq_id] = min(self.context_pos[seq_id], keep_len) |
| 2397 | |
| 2398 | def truncate(self, seq_id: int, keep_len: int) -> None: |
| 2399 | if seq_id < 0 or seq_id >= self.n_seq_max: |
no outgoing calls
no test coverage detected