Nsa trtllm mla sparse fp8 support with Deepseek v3.2 NVFP4 (#18389)

test/registered/hicache/test_nsa_pool_host_unit.py

@@ -50,6 +50,7 @@ class TestNSAHiCacheTransfer(unittest.TestCase):
             layer_num=layer_num,
             device="cuda",
             enable_memory_saver=False,
+            kv_cache_dim=576,
             index_head_dim=128,
         )
         pin_memory = io_backend == "kernel"

test/registered/kernels/test_nsa_indexer.py

@@ -232,6 +232,7 @@ class MockModelRunner:
             device=self.device,
             index_head_dim=self.config["index_head_dim"],
             enable_memory_saver=False,
+            kv_cache_dim=self.config["kv_lora_rank"] + self.config["qk_rope_head_dim"],
         )
 
         # Required by backend with NSA-specific attributes