drop ascend scheduler (#4498)

Ascend scheduler was added for non chunk prefill case before, since that
the npu ops didn't work well with chunked prefill.

Now the ops with chunked prefill work better, it's time to remove the
ascend scheduler to use vLLM default scheduler.

- vLLM version: v0.11.2

---------

Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>

tests/e2e/nightly/multi_node/config/models/DeepSeek-R1-W8A8-A2-torchair.yaml

@@ -30,7 +30,7 @@ deployment:
       --quantization ascend
       --gpu-memory-utilization 0.9
       --speculative-config '{"num_speculative_tokens": 1, "method":"deepseek_mtp"}'
-      --additional-config '{"ascend_scheduler_config":{"enabled":false},"torchair_graph_config":{"enabled":true,"enable_multistream_moe":true},"chunked_prefill_for_mla":true,"enable_weight_nz_layout":true}'
+      --additional-config '{"torchair_graph_config":{"enabled":true,"enable_multistream_moe":true},"chunked_prefill_for_mla":true,"enable_weight_nz_layout":true}'
 
   -
     server_cmd: >
@@ -51,7 +51,7 @@ deployment:
       --quantization ascend
       --gpu-memory-utilization 0.9
       --speculative-config '{"num_speculative_tokens": 1, "method":"deepseek_mtp"}'
-      --additional-config '{"ascend_scheduler_config":{"enabled":false},"torchair_graph_config":{"enabled":true,"enable_multistream_moe":true},"chunked_prefill_for_mla":true,"enable_weight_nz_layout":true}'
+      --additional-config '{"torchair_graph_config":{"enabled":true,"enable_multistream_moe":true},"chunked_prefill_for_mla":true,"enable_weight_nz_layout":true}'
 benchmarks:
   acc:
     case_type: accuracy

tests/e2e/nightly/multi_node/config/models/DeepSeek-R1-W8A8-A2.yaml

@@ -31,7 +31,7 @@ deployment:
       --gpu-memory-utilization 0.9
       --enforce-eager
       --speculative-config '{"num_speculative_tokens": 1, "method":"deepseek_mtp"}'
-      --additional-config '{"ascend_scheduler_config":{"enabled":false},"chunked_prefill_for_mla":true,"enable_weight_nz_layout":true}'
+      --additional-config '{"chunked_prefill_for_mla":true,"enable_weight_nz_layout":true}'
 
   -
     server_cmd: >
@@ -53,5 +53,5 @@ deployment:
       --gpu-memory-utilization 0.9
       --enforce-eager
       --speculative-config '{"num_speculative_tokens": 1, "method":"deepseek_mtp"}'
-      --additional-config '{"ascend_scheduler_config":{"enabled":false},"chunked_prefill_for_mla":true,"enable_weight_nz_layout":true}'
+      --additional-config '{"chunked_prefill_for_mla":true,"enable_weight_nz_layout":true}'
 benchmarks:

tests/e2e/nightly/multi_node/config/models/DeepSeek-R1-W8A8-EPLB.yaml

@@ -50,7 +50,7 @@ deployment:
           "kv_connector_module_path": "vllm_ascend.distributed.llmdatadist_c_mgr_connector"
           }'
           --additional-config
-          '{"ascend_scheduler_config":{"enabled":false},"torchair_graph_config":{"enabled":false,"enable_multistream_shared_expert":false},"enable_prefill_optimizations":true,"enable_weight_nz_layout":true,"dynamic_eplb":true,"num_iterations_eplb_update":2048,"num_wait_worker_iterations":200}'
+          '{"torchair_graph_config":{"enabled":false,"enable_multistream_shared_expert":false},"enable_prefill_optimizations":true,"enable_weight_nz_layout":true,"dynamic_eplb":true,"num_iterations_eplb_update":2048,"num_wait_worker_iterations":200}'
 
   -
     server_cmd: >
@@ -80,7 +80,7 @@ deployment:
           "kv_connector_module_path": "vllm_ascend.distributed.llmdatadist_c_mgr_connector"
           }'
           --additional-config
-          '{"ascend_scheduler_config":{"enabled":false},"torchair_graph_config":{"enabled":false,"enable_multistream_shared_expert":false},"enable_prefill_optimizations":true,"enable_weight_nz_layout":true,"dynamic_eplb":true,"num_iterations_eplb_update":2048,"num_wait_worker_iterations":200}'
+          '{"torchair_graph_config":{"enabled":false,"enable_multistream_shared_expert":false},"enable_prefill_optimizations":true,"enable_weight_nz_layout":true,"dynamic_eplb":true,"num_iterations_eplb_update":2048,"num_wait_worker_iterations":200}'
   -
     server_cmd: >
       vllm serve vllm-ascend/DeepSeek-R1-0528-W8A8
@@ -111,7 +111,7 @@ deployment:
         "kv_connector_module_path": "vllm_ascend.distributed.llmdatadist_c_mgr_connector"
         }'
         --additional-config
-        '{"ascend_scheduler_config":{"enabled":false},"torchair_graph_config":{"enabled":true,"enable_multistream_mla":true,"graph_batch_sizes":[28],"use_cached_graph":true,"enable_super_kernel":false},"multistream_overlap_shared_expert":true,"dynamic_eplb":true,"num_iterations_eplb_update":2048,"num_wait_worker_iterations":200}'
+        '{"torchair_graph_config":{"enabled":true,"enable_multistream_mla":true,"graph_batch_sizes":[28],"use_cached_graph":true,"enable_super_kernel":false},"multistream_overlap_shared_expert":true,"dynamic_eplb":true,"num_iterations_eplb_update":2048,"num_wait_worker_iterations":200}'
   -
     server_cmd: >
       vllm serve vllm-ascend/DeepSeek-R1-0528-W8A8
@@ -141,7 +141,7 @@ deployment:
         "kv_connector_module_path": "vllm_ascend.distributed.llmdatadist_c_mgr_connector"
         }'
         --additional-config
-        '{"ascend_scheduler_config":{"enabled":false},"torchair_graph_config":{"enabled":true,"enable_multistream_mla":true,"graph_batch_sizes":[28],"use_cached_graph":true,"enable_super_kernel":false},"multistream_overlap_shared_expert":true,"dynamic_eplb":true,"num_iterations_eplb_update":2048,"num_wait_worker_iterations":200}'
+        '{"torchair_graph_config":{"enabled":true,"enable_multistream_mla":true,"graph_batch_sizes":[28],"use_cached_graph":true,"enable_super_kernel":false},"multistream_overlap_shared_expert":true,"dynamic_eplb":true,"num_iterations_eplb_update":2048,"num_wait_worker_iterations":200}'
 benchmarks:
   perf:
     case_type: performance

tests/e2e/nightly/multi_node/config/models/DeepSeek-R1-W8A8.yaml

@@ -49,7 +49,7 @@ deployment:
           "kv_connector_module_path": "vllm_ascend.distributed.llmdatadist_c_mgr_connector"
           }'
           --additional-config
-          '{"ascend_scheduler_config":{"enabled":false},"torchair_graph_config":{"enabled":false,"enable_multistream_shared_expert":false},"enable_prefill_optimizations":true,"enable_weight_nz_layout":true}'
+          '{"torchair_graph_config":{"enabled":false,"enable_multistream_shared_expert":false},"enable_prefill_optimizations":true,"enable_weight_nz_layout":true}'
 
   -
     server_cmd: >
@@ -79,7 +79,7 @@ deployment:
           "kv_connector_module_path": "vllm_ascend.distributed.llmdatadist_c_mgr_connector"
           }'
           --additional-config
-          '{"ascend_scheduler_config":{"enabled":false},"torchair_graph_config":{"enabled":false,"enable_multistream_shared_expert":false},"enable_prefill_optimizations":true,"enable_weight_nz_layout":true}'
+          '{"torchair_graph_config":{"enabled":false,"enable_multistream_shared_expert":false},"enable_prefill_optimizations":true,"enable_weight_nz_layout":true}'
   -
     server_cmd: >
       vllm serve vllm-ascend/DeepSeek-R1-0528-W8A8
@@ -110,7 +110,7 @@ deployment:
         "kv_connector_module_path": "vllm_ascend.distributed.llmdatadist_c_mgr_connector"
         }'
         --additional-config
-        '{"ascend_scheduler_config":{"enabled":false},"torchair_graph_config":{"enabled":true,"enable_multistream_mla":true,"graph_batch_sizes":[28],"use_cached_graph":true,"enable_super_kernel":false},"multistream_overlap_shared_expert":true}'
+        '{"torchair_graph_config":{"enabled":true,"enable_multistream_mla":true,"graph_batch_sizes":[28],"use_cached_graph":true,"enable_super_kernel":false},"multistream_overlap_shared_expert":true}'
   -
     server_cmd: >
       vllm serve vllm-ascend/DeepSeek-R1-0528-W8A8
@@ -140,7 +140,7 @@ deployment:
         "kv_connector_module_path": "vllm_ascend.distributed.llmdatadist_c_mgr_connector"
         }'
         --additional-config
-        '{"ascend_scheduler_config":{"enabled":false},"torchair_graph_config":{"enabled":true,"enable_multistream_mla":true,"graph_batch_sizes":[28],"use_cached_graph":true,"enable_super_kernel":false},"multistream_overlap_shared_expert":true}'
+        '{"torchair_graph_config":{"enabled":true,"enable_multistream_mla":true,"graph_batch_sizes":[28],"use_cached_graph":true,"enable_super_kernel":false},"multistream_overlap_shared_expert":true}'
 benchmarks:
   perf:
     case_type: performance

tests/e2e/nightly/multi_node/config/models/DeepSeek-V3_2-Exp-bf16.yaml

@@ -29,7 +29,7 @@ deployment:
         --trust-remote-code 
         --no-enable-prefix-caching 
         --gpu-memory-utilization 0.9 
-        --additional-config '{"ascend_scheduler_config":{"enabled":true},"torchair_graph_config":{"enabled":true,"graph_batch_sizes":[16]}}'
+        --additional-config '{"torchair_graph_config":{"enabled":true,"graph_batch_sizes":[16]}}'
 
   -
     server_cmd: >
@@ -49,5 +49,5 @@ deployment:
         --trust-remote-code 
         --no-enable-prefix-caching 
         --gpu-memory-utilization 0.92 
-        --additional-config '{"ascend_scheduler_config":{"enabled":true},"torchair_graph_config":{"enabled":true,"graph_batch_sizes":[16]}}'
+        --additional-config '{"torchair_graph_config":{"enabled":true,"graph_batch_sizes":[16]}}'
 benchmarks: