Update vllm_support/README.md

vllm_support/README.md

@@ -1,7 +1,7 @@
-# KaLM-Reranker-V1-Nano vLLM Support
+# KaLM-Reranker-V1-Small vLLM Support
 
 This directory contains the experimental vLLM 0.19.1 adapter for
-`KaLM-Embedding/KaLM-Reranker-V1-Nano`. It supports offline Python and CLI
+`KaLM-Embedding/KaLM-Reranker-V1-Small`. It supports offline Python and CLI
 reranking plus an optional FastAPI service.
 
 The adapter does not modify or retrain the checkpoint. It reads the original
@@ -35,9 +35,9 @@ conda activate kalm-vllm
 pip install "vllm==0.19.1" "transformers==5.6.2"
 pip install "fastapi>=0.136,<0.137" "uvicorn>=0.46,<0.47"
 
-hf download KaLM-Embedding/KaLM-Reranker-V1-Nano \
-  --local-dir ./KaLM-Reranker-V1-Nano
-pip install ./KaLM-Reranker-V1-Nano/vllm_support --no-deps
+hf download KaLM-Embedding/KaLM-Reranker-V1-Small \
+  --local-dir ./KaLM-Reranker-V1-Small
+pip install ./KaLM-Reranker-V1-Small/vllm_support --no-deps
 export VLLM_PLUGINS=kalm_t5gemma2
 ```
 
@@ -45,10 +45,10 @@ The model can also be loaded directly by its Hugging Face ID. In that case,
 only download the `vllm_support` directory before installing the plugin:
 
 ```bash
-hf download KaLM-Embedding/KaLM-Reranker-V1-Nano \
+hf download KaLM-Embedding/KaLM-Reranker-V1-Small \
   --include "vllm_support/**" \
-  --local-dir ./KaLM-Reranker-V1-Nano
-pip install ./KaLM-Reranker-V1-Nano/vllm_support --no-deps
+  --local-dir ./KaLM-Reranker-V1-Small
+pip install ./KaLM-Reranker-V1-Small/vllm_support --no-deps
 ```
 
 ## Offline Python API
@@ -64,7 +64,7 @@ documents = [
 
 pairs = [(query, document) for document in documents]
 with KaLMVLLMReranker(
-    "KaLM-Embedding/KaLM-Reranker-V1-Nano",
+    "KaLM-Embedding/KaLM-Reranker-V1-Small",
     query_max_length=512,
     document_max_length=1024,
     encoder_chunk_size=4,
@@ -97,7 +97,7 @@ Score JSONL input:
 
 ```bash
 kalm-vllm-rerank \
-  --input-jsonl ./KaLM-Reranker-V1-Nano/vllm_support/examples/sample_pairs.jsonl \
+  --input-jsonl ./KaLM-Reranker-V1-Small/vllm_support/examples/sample_pairs.jsonl \
   --output-jsonl ./scores.jsonl \
   --return-margin
 ```
@@ -114,7 +114,7 @@ Start one model instance:
 kalm-vllm-serve \
   --host 0.0.0.0 \
   --port 8000 \
-  --model KaLM-Embedding/KaLM-Reranker-V1-Nano \
+  --model KaLM-Embedding/KaLM-Reranker-V1-Small \
   --encoder-chunk-size 4
 ```
 
@@ -123,7 +123,7 @@ variables:
 
 ```bash
 CUDA_VISIBLE_DEVICES=0 PORT=8000 \
-  ./KaLM-Reranker-V1-Nano/vllm_support/examples/start_online_server.sh
+  ./KaLM-Reranker-V1-Small/vllm_support/examples/start_online_server.sh
 ```
 
 In a second terminal, check health and send built-in demo requests:
@@ -140,7 +140,7 @@ one query against multiple documents:
 ```bash
 kalm-vllm-client \
   --endpoint rerank \
-  --json-file ./KaLM-Reranker-V1-Nano/vllm_support/examples/rerank_request.json \
+  --json-file ./KaLM-Reranker-V1-Small/vllm_support/examples/rerank_request.json \
   --return-margin \
   --top-k 10
 ```
@@ -150,7 +150,7 @@ Use `/score` for a batch of independent query-document pairs:
 ```bash
 kalm-vllm-client \
   --endpoint score \
-  --json-file ./KaLM-Reranker-V1-Nano/vllm_support/examples/score_request.json \
+  --json-file ./KaLM-Reranker-V1-Small/vllm_support/examples/score_request.json \
   --return-margin
 ```
 
@@ -247,7 +247,7 @@ Reinstall the package and ensure the environment variable includes its entry
 point name:
 
 ```bash
-pip install ./KaLM-Reranker-V1-Nano/vllm_support --no-deps --force-reinstall
+pip install ./KaLM-Reranker-V1-Small/vllm_support --no-deps --force-reinstall
 export VLLM_PLUGINS=kalm_t5gemma2
 ```
 
@@ -258,22 +258,10 @@ sensitive.
 
 **The tokenizer check fails**
 
-Confirm that the tokenizer belongs to this Nano checkpoint. The adapter
+Confirm that the tokenizer belongs to this Small checkpoint. The adapter
 requires `yes -> 4443` and `no -> 1904`.
 
 **CUDA runs out of memory**
 
 Reduce `batch_size`, `document_max_length`, `query_max_length`,
 `max_model_len`, or `gpu_memory_utilization`.
-
-**CUDA initialization fails with error 803**
-
-The process may be resolving a CUDA compatibility library before the host
-driver library. On common Debian/Ubuntu layouts, retry with:
-
-```bash
-export LD_LIBRARY_PATH="/lib/x86_64-linux-gnu:/usr/lib/x86_64-linux-gnu${LD_LIBRARY_PATH:+:$LD_LIBRARY_PATH}"
-```
-
-The provided `start_online_server.sh` applies this adjustment automatically
-when both directories exist.