[README] Update README.md. (#435)

intel · Jun 5, 2024 · f2bb303 · f2bb303
1 parent 669bd66
commit f2bb303
Show file tree

Hide file tree

Showing 3 changed files with 6 additions and 6 deletions.
diff --git a/README.md b/README.md
@@ -337,8 +337,8 @@ pip install vllm-xft
 export $(python -c 'import xfastertransformer as xft; print(xft.get_env())')
 
 python -m vllm.entrypoints.openai.api_server \
-        --model ${XFT_MODEL} \
-        --tokenizer ${TOKENIZER_DIR} \
+        --model ${MODEL_PATH} \
+        --tokenizer ${TOKEN_PATH} \
         --dtype bf16 \
         --kv-cache-dtype fp16 \
         --served-model-name xft \

diff --git a/README_CN.md b/README_CN.md
@@ -340,8 +340,8 @@ pip install vllm-xft
 export $(python -c 'import xfastertransformer as xft; print(xft.get_env())')
 
 python -m vllm.entrypoints.openai.api_server \
-        --model ${XFT_MODEL} \
-        --tokenizer ${TOKENIZER_DIR} \
+        --model ${MODEL_PATH} \
+        --tokenizer ${TOKEN_PATH} \
         --dtype bf16 \
         --kv-cache-dtype fp16 \
         --served-model-name xft \

diff --git a/serving/vllm-xft.md b/serving/vllm-xft.md
@@ -15,8 +15,8 @@ pip install vllm-xft
 export $(python -c 'import xfastertransformer as xft; print(xft.get_env())')
 
 python -m vllm.entrypoints.openai.api_server \
-        --model ${XFT_MODEL} \
-        --tokenizer ${TOKENIZER_DIR} \
+        --model ${MODEL_PATH} \
+        --tokenizer ${TOKEN_PATH} \
         --dtype bf16 \
         --kv-cache-dtype fp16 \
         --served-model-name xft \