Remove stale layer_transfer_counter prefetch guards (port from e293d4a39 fix #3)
CpSharedKVMlaPrefetcher.create and CpSharedKVIndexPrefetcher.create returned None whenever ``token_to_kv_pool.layer_transfer_counter`` was set, which permanently disables NSA indexer prefetch whenever HiCache is active — even when no H2D transfer is in progress. The guard is unnecessary: buffer getters synchronize via wait_until(), and the prefetcher's stream calls wait_stream(current_stream) before materialization. Removing it restores intended prefetch parallelism under HiCache + NSA. Only fix #3 of e293d4a39 is portable to this branch — fixes #1 (SHM timeout) and #2 (SHM exception safety) target shm_allreduce.py and the batched-CP coordination path in hiradix_cache.py, neither of which exists here. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This commit is contained in:
@@ -178,9 +178,6 @@ class CpSharedKVMlaPrefetcher:
|
||||
if token_to_kv_pool is None:
|
||||
_prefetch_log("create_skip reason=missing_token_to_kv_pool")
|
||||
return None
|
||||
if getattr(token_to_kv_pool, "layer_transfer_counter", None) is not None:
|
||||
_prefetch_log("create_skip reason=layer_transfer_active")
|
||||
return None
|
||||
|
||||
layout = getattr(forward_batch, "cp_shared_kv_layout", None)
|
||||
if layout is None:
|
||||
@@ -705,12 +702,6 @@ class CpSharedKVIndexPrefetcher:
|
||||
"forward batch has no token_to_kv_pool.",
|
||||
)
|
||||
return None
|
||||
if getattr(token_to_kv_pool, "layer_transfer_counter", None) is not None:
|
||||
_index_prefetch_fallback_log(
|
||||
"layer_transfer_active",
|
||||
"layer transfer is active.",
|
||||
)
|
||||
return None
|
||||
|
||||
layout = getattr(forward_batch, "cp_shared_kv_layout", None)
|
||||
if layout is None:
|
||||
|
||||
Reference in New Issue
Block a user