Merge #2624 review updates into the GLM-5.3-Flash branch

Keep this branch's live-MTP export, mtp.* rules and KPool indexer export: GLM-5.3-Flash's bridge
builds the MTP, so the guard #2624 adds for GLM-5 does not apply here. Takes the DSA test check.

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Signed-off-by: Keval Morabia <28916987+kevalmorabia97@users.noreply.github.com>

Author: kevalmorabia97

tests/gpu_megatron/torch/quantization/plugins/test_megatron.py

@@ -1958,6 +1958,11 @@ def _test_dsa_kv_cache_quant_helper(tmp_path, rank, size):
         if ".indexer." in name:
             param.requires_grad_(False)
     sharded_state_dict_test_helper(tmp_path, model, model_test, forward)
+    # The helper compares every restored tensor (incl. K/V amax), but V is unused in the forward
+    # pass, so also check both quantizers came back enabled.
+    restored = [m for m in model_test.modules() if isinstance(m, DSAttention)]
+    assert len(restored) == len(dsa_modules)
+    assert all(m.k_bmm_quantizer.is_enabled and m.v_bmm_quantizer.is_enabled for m in restored)
 
 
 def test_dsa_kv_cache_quant(dist_workers_size_1, tmp_path):