EngineX-Hygon/sglang
5
0
Fork 0
Code Issues Pull Requests Actions 7 Projects Releases Wiki Activity

Fix Docs CI When Compile Error (#2323)

Browse Source
This commit is contained in:
Chayenne
2024-12-04 11:19:46 -08:00
committed by GitHub
parent 2db4469808
commit 786be44da5
3 changed files with 7 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
docs/Makefile
View File

@@ -19,7 +19,7 @@ compile:
echo "Executing $$nb"; \ echo "Executing $$nb"; \
jupyter nbconvert --to notebook --execute --inplace "$$nb" \ jupyter nbconvert --to notebook --execute --inplace "$$nb" \
--ExecutePreprocessor.timeout=600 \ --ExecutePreprocessor.timeout=600 \
--ExecutePreprocessor.kernel_name=python3; \ --ExecutePreprocessor.kernel_name=python3 || exit 1; \
fi; \ fi; \
done done

10
docs/backend/native_api.ipynb
View File

@@ -220,19 +220,19 @@
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
"# failed update with different parameter size\n", "# failed update with different parameter size or wrong name\n",
"\n", "\n",
"url = \"http://localhost:30010/update_weights_from_disk\"\n", "url = \"http://localhost:30010/update_weights_from_disk\"\n",
"data = {\"model_path\": \"meta-llama/Llama-3.2-3B\"}\n", "data = {\"model_path\": \"meta-llama/Llama-3.2-1B-wrong\"}\n",
"\n", "\n",
"response = requests.post(url, json=data)\n", "response = requests.post(url, json=data)\n",
"response_json = response.json()\n", "response_json = response.json()\n",
"print_highlight(response_json)\n", "print_highlight(response_json)\n",
"assert response_json[\"success\"] is False\n", "assert response_json[\"success\"] is False\n",
"assert response_json[\"message\"] == (\n", "assert response_json[\"message\"] == (\n",
" \"Failed to update weights: The size of tensor a (2048) must match \"\n", " \"Failed to get weights iterator: \"\n",
" \"the size of tensor b (3072) at non-singleton dimension 1.\\n\"\n", " \"meta-llama/Llama-3.2-1B-wrong\"\n",
" \"Rolling back to original weights.\"\n", " \" (repository not found).\"\n",
")" ")"
] ]
}, },

2
python/sglang/srt/server.py
View File

@@ -329,7 +329,7 @@ async def encode_request(obj: EmbeddingReqInput, request: Request):
) )
@app.api_route("/encode", methods=["POST", "PUT"]) @app.api_route("/classify", methods=["POST", "PUT"])
@time_func_latency @time_func_latency
async def classify_request(obj: EmbeddingReqInput, request: Request): async def classify_request(obj: EmbeddingReqInput, request: Request):
"""Handle a reward model request. Now the arguments and return values are the same as embedding models.""" """Handle a reward model request. Now the arguments and return values are the same as embedding models."""