[TopK] Follow-up fixes to the persistent top-k kernels
- Counter enum declared above the decode template (two-phase lookup). - Emission-fault flag set atomically. - Close the legacy large tie loop with a block barrier (inherited). - Large-path fault injectors registered as hashed passthroughs. - The tensor-free counter-slots op registered for CompositeExplicitAutograd. - Tie measurements recorded only on rows neither fault verdict failed. - Tests scoped to the properties the build promises. Co-Authored-By: Hinata <hinata@idihore.id> Signed-off-by: MOVZX <movzx@yahoo.com>
This commit is contained in:
@@ -865,8 +865,6 @@ STABLE_TORCH_LIBRARY_IMPL(_C, CUDA, ops) {
|
||||
ops.impl("persistent_topk", TORCH_BOX(&persistent_topk));
|
||||
ops.impl("persistent_topk_exact_counters",
|
||||
TORCH_BOX(&persistent_topk_exact_counters));
|
||||
ops.impl("persistent_topk_exact_counters_slots",
|
||||
TORCH_BOX(&persistent_topk_exact_counters_slots));
|
||||
#ifdef VLLM_ENABLE_COOPERATIVE_TOPK
|
||||
ops.impl("cooperative_topk", TORCH_BOX(&cooperative_topk));
|
||||
#endif
|
||||
@@ -943,6 +941,12 @@ STABLE_TORCH_LIBRARY_IMPL(_C, CompositeExplicitAutograd, ops) {
|
||||
ops.impl("cutlass_scaled_mm_supports_fp4",
|
||||
TORCH_BOX(&cutlass_scaled_mm_supports_fp4));
|
||||
#endif
|
||||
// Tensor-free: the counter layout the BUILD carries. Registered here, not
|
||||
// in the CUDA block -- with no tensor argument there is no dispatch key, so
|
||||
// a CUDA-only registration can never be called (reference host:
|
||||
// NotImplementedError "no fallback function is registered").
|
||||
ops.impl("persistent_topk_exact_counters_slots",
|
||||
TORCH_BOX(&persistent_topk_exact_counters_slots));
|
||||
}
|
||||
|
||||
// Cache ops
|
||||
|
||||
Reference in New Issue
Block a user