[https://nvbugs/5457504][fix] fix kv cache event test in disaggregated worker tests (#7028)

Signed-off-by: zhengd-nv <[email protected]>

Author: zhengd-nv

tests/integration/defs/disaggregated/test_workers.py

@@ -298,7 +298,8 @@ async def multi_round_request(self,
 
         if check_match_count:
             assert ctx_match_count > 0
-            assert gen_match_count >= ctx_match_count
+            assert gen_match_count > 0
+            assert gen_match_count >= ctx_match_count or gen_evicted
         return request["prompt"]
 
     async def test_multi_round_request(self,
@@ -310,6 +311,8 @@ async def test_multi_round_request(self,
                 for prompt in init_prompts
             ]
             prompts = await asyncio.gather(*chat_threads)
+            # send a request to flush events
+            await self.multi_round_request(session, init_prompts[0], 1, False)
             await asyncio.gather(*[
                 self.multi_round_request(session, prompt, 1, True)
                 for prompt in prompts

tests/integration/test_lists/waives.txt

@@ -287,7 +287,6 @@ test_e2e.py::test_ptp_quickstart_advanced[Llama3.1-70B-FP8-llama-3.1-model/Llama
 accuracy/test_llm_api_pytorch.py::TestMistralSmall24B::test_auto_dtype SKIP (https://nvbugs/5454875)
 examples/test_llm_api_with_mpi.py::test_llm_api_single_gpu_with_mpirun[TinyLlama-1.1B-Chat-v1.0] SKIP (https://nvbugs/5434372)
 triton_server/test_triton.py::test_gpt_ib[gpt-ib] SKIP (https://nvbugs/5431116)
-disaggregated/test_workers.py::test_workers_kv_cache_events[TinyLlama-1.1B-Chat-v1.0] SKIP (https://nvbugs/5457504)
 accuracy/test_llm_api.py::TestMistralNemo12B::test_fp8 SKIP (https://nvbugs/5413197)
 triton_server/test_triton.py::test_gpt_ib_streaming[gpt-ib-streaming] SKIP (https://nvbugs/5371349)
 triton_server/test_triton.py::test_gpt_ib_ptuning[gpt-ib-ptuning] SKIP (https://nvbugs/5445624)