dylanyunlong/project_6
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

baseline4 NAN 0X7FFF7FFF

Browse Source
This commit is contained in:
root
2026-08-18 08:37:30 +00:00
parent ab078989da
commit 7a02a5bf92
1 changed files with 9 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

11
qwen3_6_scripts/mamba_cache.py
View File

@@ -208,7 +208,14 @@ class MambaCacheManager:
finished_seq_groups_req_ids: List[str]):
for req_id in finished_seq_groups_req_ids:
if req_id in self.mamba_cache_indices_mapping:
self.mamba_cache_indices_mapping.pop(req_id)
seq_mapping = self.mamba_cache_indices_mapping.pop(req_id)
# Zero out released cache slots so new requests start from
# clean state. Without this, a new prefill reuses the stale
# temporal_state of the previous (unrelated) request, causing
# the GDN delta-rule to diverge → NaN → GPU memory corruption.
for cache_idx in seq_mapping.values():
for cache_t in self.mamba_cache:
cache_t[:, cache_idx].zero_()
def _first_free_index_in_mamba_cache(
self, indices_range: Optional[List[int]] = None) -> int:
@@ -221,4 +228,4 @@ class MambaCacheManager:
if i not in all_occupied_indices:
return i
raise Exception("Couldn't find a free spot in the mamba cache! This"
"should never happen")
"should never happen")