Drop torchair (#4814)

aclgraph is stable and fast now. Let's drop torchair graph mode now.

TODO: some logic to adapt torchair should be cleaned up as well. We'll
do it in the following PR.

- vLLM version: v0.12.0
- vLLM main:
ad32e3e19c

Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
Co-authored-by: Mengqing Cao <cmq0113@163.com>

docs/source/tutorials/DeepSeek-V3.1.md

@@ -128,9 +128,8 @@ vllm serve /weights/DeepSeek-V3.1_w8a8mix_mtp \
 --trust-remote-code \
 --no-enable-prefix-caching \
 --gpu-memory-utilization 0.92 \
---speculative-config '{"num_speculative_tokens": 1, "method": "deepseek_mtp"}' \
+--speculative-config '{"num_speculative_tokens": 1, "method": "mtp"}' \
 --compilation-config '{"cudagraph_mode": "FULL_DECODE_ONLY"}' \
---additional-config '{"torchair_graph_config":{"enabled":false}}'
 ```
 
 ### Multi-node Deployment
@@ -190,9 +189,8 @@ vllm serve /weights/DeepSeek-V3.1_w8a8mix_mtp \
 --trust-remote-code \
 --no-enable-prefix-caching \
 --gpu-memory-utilization 0.94 \
---speculative-config '{"num_speculative_tokens": 1, "method": "deepseek_mtp"}' \
+--speculative-config '{"num_speculative_tokens": 1, "method": "mtp"}' \
 --compilation-config '{"cudagraph_mode": "FULL_DECODE_ONLY"}' \
---additional-config '{"torchair_graph_config":{"enabled":false}}'
 ```
 
 **Node 1**
@@ -247,9 +245,8 @@ vllm serve /weights/DeepSeek-V3.1_w8a8mix_mtp \
 --trust-remote-code \
 --no-enable-prefix-caching \
 --gpu-memory-utilization 0.94 \
---speculative-config '{"num_speculative_tokens": 1, "method": "deepseek_mtp"}' \
+--speculative-config '{"num_speculative_tokens": 1, "method": "mtp"}' \
 --compilation-config '{"cudagraph_mode": "FULL_DECODE_ONLY"}' \
---additional-config '{"torchair_graph_config":{"enabled":false}}'
 ```
 
 ### Prefill-Decode Disaggregation
@@ -421,7 +418,7 @@ vllm serve /weights/DeepSeek-V3.1_w8a8mix_mtp \
   --gpu-memory-utilization 0.9 \
   --quantization ascend \
   --no-enable-prefix-caching \
-  --speculative-config '{"num_speculative_tokens": 1, "method": "deepseek_mtp"}' \
+  --speculative-config '{"num_speculative_tokens": 1, "method": "mtp"}' \
   --additional-config '{"recompute_scheduler_enable":true,"enable_shared_expert_dp": true}' \
   --kv-transfer-config \
   '{"kv_connector": "MooncakeConnector",

docs/source/tutorials/DeepSeek-V3.2-Exp.md

@@ -173,8 +173,7 @@ vllm serve vllm-ascend/DeepSeek-V3.2-Exp-W8A8 \
 --enable-expert-parallel \
 --trust-remote-code \
 --no-enable-prefix-caching \
---gpu-memory-utilization 0.92 \
---additional-config '{"torchair_graph_config":{"enabled":true,"graph_batch_sizes":[16]}}'
+--gpu-memory-utilization 0.92
 ```
 
 ### Multi-node Deployment
@@ -225,8 +224,7 @@ vllm serve /root/.cache/Modelers_Park/DeepSeek-V3.2-Exp \
 --max-num-batched-tokens 17450 \
 --trust-remote-code \
 --no-enable-prefix-caching \
---gpu-memory-utilization 0.9 \
---additional-config '{"torchair_graph_config":{"enabled":true,"graph_batch_sizes":[16]}}'
+--gpu-memory-utilization 0.9
 ```
 
 **Node 1**
@@ -269,8 +267,7 @@ vllm serve /root/.cache/Modelers_Park/DeepSeek-V3.2-Exp \
 --enable-expert-parallel \
 --trust-remote-code \
 --no-enable-prefix-caching \
---gpu-memory-utilization 0.92 \
---additional-config '{"torchair_graph_config":{"enabled":true,"graph_batch_sizes":[16]}}'
+--gpu-memory-utilization 0.92
 ```
 
 ::::
@@ -316,8 +313,7 @@ vllm serve vllm-ascend/DeepSeek-V3.2-Exp-W8A8 \
 --trust-remote-code \
 --quantization ascend \
 --no-enable-prefix-caching \
---gpu-memory-utilization 0.9 \
---additional-config '{"torchair_graph_config":{"enabled":true,"graph_batch_sizes":[16]}}'
+--gpu-memory-utilization 0.9
 ```
 
 **Node 1**
@@ -362,8 +358,7 @@ vllm serve vllm-ascend/DeepSeek-V3.2-Exp-W8A8 \
 --trust-remote-code \
 --quantization ascend \
 --no-enable-prefix-caching \
---gpu-memory-utilization 0.92 \
---additional-config '{"torchair_graph_config":{"enabled":true,"graph_batch_sizes":[16]}}'
+--gpu-memory-utilization 0.92
 ```
 
 ::::

docs/source/tutorials/multi_node.md

@@ -136,8 +136,7 @@ vllm serve vllm-ascend/DeepSeek-V3.1-W8A8 \
 --max-num-batched-tokens 8192 \
 --trust-remote-code \
 --no-enable-prefix-caching \
---gpu-memory-utilization 0.9 \
---additional-config '{"torchair_graph_config":{"enabled":true}}'
+--gpu-memory-utilization 0.9
 ```
 
 **Node 1**
@@ -181,8 +180,7 @@ vllm serve vllm-ascend/DeepSeek-V3.1-W8A8 \
 --enable-expert-parallel \
 --trust-remote-code \
 --no-enable-prefix-caching \
---gpu-memory-utilization 0.92 \
---additional-config '{"torchair_graph_config":{"enabled":true}}'
+--gpu-memory-utilization 0.92
 ```
 
 The deployment view looks like:

docs/source/tutorials/multi_node_kimi.md

@@ -92,8 +92,7 @@ vllm serve /home/cache/weights/Kimi-K2-Instruct-W8A8 \
 --max-num-batched-tokens 8192 \
 --trust-remote-code \
 --no-enable-prefix-caching \
---gpu-memory-utilization 0.9 \
---additional-config '{"torchair_graph_config":{"enabled":true}}'
+--gpu-memory-utilization 0.9
 ```
 
 **Node 1**
@@ -136,8 +135,7 @@ vllm serve /home/cache/weights/Kimi-K2-Instruct-W8A8 \
 --enable-expert-parallel \
 --trust-remote-code \
 --no-enable-prefix-caching \
---gpu-memory-utilization 0.92 \
---additional-config '{"torchair_graph_config":{"enabled":true}}'
+--gpu-memory-utilization 0.92
 ```
 
 The deployment view looks like:

docs/source/tutorials/multi_npu_moge.md

@@ -153,12 +153,7 @@ if __name__ == "__main__":
             enable_expert_parallel=True,
             distributed_executor_backend="mp",
             max_model_len=1024,
-            trust_remote_code=True,
-            additional_config={
-            'torchair_graph_config': {
-            'enabled': True,
-            }
-            })
+            trust_remote_code=True)
 
     outputs = llm.generate(prompts, sampling_params)
     for output in outputs: