[Pooling] Fix Rust pooling endpoint for benchmark (#53352)

Signed-off-by: Taneem Ibrahim <taneem.ibrahim@gmail.com>

rust/src/bench/README.md

@@ -419,7 +419,7 @@ vllm-bench \
 | --------- | ------------- | ------------- |
 | `openai-embeddings` | `/v1/embeddings` | Text embedding (accepts text or token IDs) |
 | `openai-embeddings-chat` | `/v1/embeddings` | Chat-format embedding (supports multimodal content) |
-| `vllm-pooling` | `/v1/pooling` | vLLM native pooling endpoint |
+| `vllm-pooling` | `/pooling` | vLLM native pooling endpoint |
 | `vllm-rerank` | `/v1/rerank` | vLLM reranking (query from prompt, documents via `--extra-body`) |
 
 Pooling backends are non-streaming and report E2EL (end-to-end latency) only. Use `--dataset-name sharegpt`, `sonnet`, or `hf` for text-based embedding/rerank benchmarks, or `random` for token-ID-based embedding benchmarks.

rust/src/bench/src/backends/pooling.rs

@@ -8,7 +8,7 @@
 //! - `openai-embeddings`: Standard OpenAI `/v1/embeddings` with text input
 //! - `openai-embeddings-chat`: OpenAI `/v1/embeddings` with chat message format (supports
 //!   multimodal)
-//! - `vllm-pooling`: vLLM `/v1/pooling` endpoint
+//! - `vllm-pooling`: vLLM `/pooling` endpoint
 //! - `vllm-rerank`: vLLM `/v1/rerank` endpoint (query + documents)
 
 use std::time::Instant;

rust/src/bench/src/cli.rs

@@ -682,7 +682,7 @@ impl BenchServeArgs {
             BackendKind::OpenaiEmbeddings | BackendKind::OpenaiEmbeddingsChat => {
                 "/v1/embeddings".to_string()
             }
-            BackendKind::VllmPooling => "/v1/pooling".to_string(),
+            BackendKind::VllmPooling => "/pooling".to_string(),
             BackendKind::VllmRerank => "/v1/rerank".to_string(),
         }
     }