94057c3d3e
PR Test (NPU) / check-changes (push) Has been cancelled
PR Test (NPU) / pr-gate (push) Has been cancelled
PR Test (NPU) / set-image-config (push) Has been cancelled
PR Test (NPU) / stage-b-test-1-npu-a2 (0) (push) Has been cancelled
PR Test (NPU) / stage-b-test-1-npu-a2 (1) (push) Has been cancelled
PR Test (NPU) / stage-b-test-2-npu-a2 (0) (push) Has been cancelled
PR Test (NPU) / stage-b-test-2-npu-a2 (1) (push) Has been cancelled
PR Test (NPU) / stage-b-test-4-npu-a3 (push) Has been cancelled
PR Test (NPU) / stage-b-test-16-npu-a3 (push) Has been cancelled
PR Test (NPU) / multimodal-gen-test-1-npu-a3 (push) Has been cancelled
PR Test (NPU) / multimodal-gen-test-2-npu-a3 (push) Has been cancelled
PR Test (Arm64) / pr-gate (push) Has been cancelled
PR Test (Arm64) / check-changes (push) Has been cancelled
PR Test (Arm64) / build-test (push) Has been cancelled
PR Test (sgl-router) / gate (push) Has been cancelled
PR Test (sgl-router) / tier-1 — lint (push) Has been cancelled
PR Test (sgl-router) / tier-2 — build + test (push) Has been cancelled
PR Test (sgl-router) / tier-3 — docker (placeholder) (push) Has been cancelled
PR Test (sgl-router) / tier-3 — k8s integration (push) Has been cancelled
PR Test (sgl-router) / tier-3 — e2e (push) Has been cancelled
PR Test (sgl-router) / finish (push) Has been cancelled
PR Test (NPU) / single-node-poc (map[name:qwen3_6_27b_w8a8_1p_in64k_out1k_50ms runner:linux-aarch64-a3-2 test_case:test/registered/ascend/performance/qwen3_6_27b/test_npu_qwen3_6_27b_w8a8_1p_in64k_out1k_50ms.py test_type:perf]) (push) Has been cancelled
PR Test (NPU) / pr-test-npu-finish (push) Has been cancelled
PR Test (Xeon) / pr-gate (push) Has been cancelled
PR Test (Xeon) / check-changes (push) Has been cancelled
PR Test (Xeon) / build-test (, xeon-gnr, base-b-test-cpu) (push) Has been cancelled
PR Test (XPU) / check-changes (push) Has been cancelled
PR Test (XPU) / pr-gate (push) Has been cancelled
PR Test (XPU) / stage-a-test-1-gpu-xpu (push) Has been cancelled
PR Test (XPU) / wait-for-stage-a (push) Has been cancelled
PR Test (XPU) / stage-b-test-1-gpu-xpu (push) Has been cancelled
PR Test (XPU) / finish (push) Has been cancelled
CI Model Inventory / build-inventory (push) Has been cancelled
Lint / lint (push) Has been cancelled
PR Benchmark (SMG Components) / Benchmark Compilation Check (push) Has been cancelled
PR Benchmark (SMG Components) / Benchmark - Manual Policy (push) Has been cancelled
PR Benchmark (SMG Components) / Benchmark - Request Processing (push) Has been cancelled
PR Benchmark (SMG Components) / Benchmark Summary (push) Has been cancelled
PR Test (SMG) / build-wheel (push) Has been cancelled
Release SGLang Model Gateway to PyPI / build on windows (x86_64 - auto) (push) Has been cancelled
Release SGLang Model Gateway to PyPI / build on macos (x86_64 - auto) (push) Has been cancelled
PR Test (SMG) / python-unit-tests (push) Has been cancelled
PR Test (SMG) / unit-tests (push) Has been cancelled
PR Test (SMG) / benchmarks (push) Has been cancelled
PR Test (SMG) / chat-completions (push) Has been cancelled
PR Test (SMG) / chat-completions-4gpu (push) Has been cancelled
PR Test (SMG) / e2e (push) Has been cancelled
PR Test (SMG) / docker-build-test (push) Has been cancelled
PR Test (SMG) / k8s-integration (push) Has been cancelled
PR Test (SMG) / finish (push) Has been cancelled
PR Test (SMG) / summarize-benchmarks (push) Has been cancelled
Release SGLang Model Gateway Docker Image / publish (push) Has been cancelled
Release SGLang Model Gateway to PyPI / build on macos (aarch64 - auto) (push) Has been cancelled
Release SGLang Model Gateway to PyPI / build on linux (aarch64 - auto) (push) Has been cancelled
Release SGLang Model Gateway to PyPI / build on linux (x86_64 - auto) (push) Has been cancelled
Release SGLang Model Gateway to PyPI / build on linux (aarch64 - musllinux_1_1) (push) Has been cancelled
Release SGLang Model Gateway to PyPI / build on linux (x86_64 - musllinux_1_1) (push) Has been cancelled
Release SGLang Model Gateway to PyPI / Build SDist (push) Has been cancelled
Release SGLang Model Gateway to PyPI / Upload to PyPI (push) Has been cancelled
Release SGLang Kernels / build-cu129-matrix (aarch64, 12.9, 3.10, arm-kernel-build-node) (push) Has been cancelled
Release SGLang Kernels / build-cu129-matrix (x86_64, 12.9, 3.10, x64-kernel-build-node) (push) Has been cancelled
Release SGLang Kernels / release-cu129 (push) Has been cancelled
Release SGLang Kernels / build-cu130-matrix (aarch64, 13.0, 3.10, arm-kernel-build-node) (push) Has been cancelled
Release SGLang Kernels / build-cu130-matrix (x86_64, 13.0, 3.10, x64-kernel-build-node) (push) Has been cancelled
Release SGLang Kernels / release-cu130 (push) Has been cancelled
Release SGLang Kernels / build-rocm-matrix (3.10, 700) (push) Has been cancelled
Release SGLang Kernels / build-rocm-matrix (3.10, 720) (push) Has been cancelled
Release SGLang Kernels / release-rocm700 (push) Has been cancelled
Release SGLang Kernels / release-rocm720 (push) Has been cancelled
Release SGLang Kernels / build-musa43 (43, 3.10) (push) Has been cancelled
Release SGLang Kernels / release-musa43 (push) Has been cancelled
110 lines
2.6 KiB
Python
110 lines
2.6 KiB
Python
"""
|
|
Usage:
|
|
python -m sglang.launch_server --model-path meta-llama/Llama-2-7b-chat-hf --port 30000
|
|
python readme_examples.py
|
|
"""
|
|
|
|
import sglang as sgl
|
|
|
|
|
|
@sgl.function
|
|
def tool_use(s, question):
|
|
s += "To answer this question: " + question + ". "
|
|
s += (
|
|
"I need to use a "
|
|
+ sgl.gen("tool", choices=["calculator", "search engine"])
|
|
+ ". "
|
|
)
|
|
|
|
if s["tool"] == "calculator":
|
|
s += "The math expression is" + sgl.gen("expression")
|
|
elif s["tool"] == "search engine":
|
|
s += "The key word to search is" + sgl.gen("word")
|
|
|
|
|
|
@sgl.function
|
|
def tip_suggestion(s):
|
|
s += (
|
|
"Here are two tips for staying healthy: "
|
|
"1. Balanced Diet. 2. Regular Exercise.\n\n"
|
|
)
|
|
|
|
forks = s.fork(2)
|
|
for i, f in enumerate(forks):
|
|
f += f"Now, expand tip {i+1} into a paragraph:\n"
|
|
f += sgl.gen(f"detailed_tip", max_tokens=256, stop="\n\n")
|
|
|
|
s += "Tip 1:" + forks[0]["detailed_tip"] + "\n"
|
|
s += "Tip 2:" + forks[1]["detailed_tip"] + "\n"
|
|
s += "In summary" + sgl.gen("summary")
|
|
|
|
|
|
@sgl.function
|
|
def regular_expression_gen(s):
|
|
s += "Q: What is the IP address of the Google DNS servers?\n"
|
|
s += "A: " + sgl.gen(
|
|
"answer",
|
|
temperature=0,
|
|
regex=r"((25[0-5]|2[0-4]\d|[01]?\d\d?).){3}(25[0-5]|2[0-4]\d|[01]?\d\d?)",
|
|
)
|
|
|
|
|
|
@sgl.function
|
|
def text_qa(s, question):
|
|
s += "Q: " + question + "\n"
|
|
s += "A:" + sgl.gen("answer", stop="\n")
|
|
|
|
|
|
def driver_tool_use():
|
|
state = tool_use.run(question="What is the capital of the United States?")
|
|
print(state.text())
|
|
print("\n")
|
|
|
|
|
|
def driver_tip_suggestion():
|
|
state = tip_suggestion.run()
|
|
print(state.text())
|
|
print("\n")
|
|
|
|
|
|
def driver_regex():
|
|
state = regular_expression_gen.run()
|
|
print(state.text())
|
|
print("\n")
|
|
|
|
|
|
def driver_batching():
|
|
states = text_qa.run_batch(
|
|
[
|
|
{"question": "What is the capital of the United Kingdom?"},
|
|
{"question": "What is the capital of France?"},
|
|
{"question": "What is the capital of Japan?"},
|
|
],
|
|
progress_bar=True,
|
|
)
|
|
|
|
for s in states:
|
|
print(s.text())
|
|
print("\n")
|
|
|
|
|
|
def driver_stream():
|
|
state = text_qa.run(
|
|
question="What is the capital of France?", temperature=0.1, stream=True
|
|
)
|
|
|
|
for out in state.text_iter():
|
|
print(out, end="", flush=True)
|
|
print("\n")
|
|
|
|
|
|
if __name__ == "__main__":
|
|
# sgl.set_default_backend(sgl.OpenAI("gpt-3.5-turbo-instruct"))
|
|
sgl.set_default_backend(sgl.RuntimeEndpoint("http://localhost:30000"))
|
|
|
|
driver_tool_use()
|
|
driver_tip_suggestion()
|
|
driver_regex()
|
|
driver_batching()
|
|
driver_stream()
|