mirror of
https://github.com/hanzoai/engine.git
synced 2026-11-20 14:17:52 +00:00
* Add mxfp4 gemm and grouped gemm support * Support gpt-oss! * Closer * Fix something with rope * FUlly works * Cleanup * Normal sampling * Better masks * Fused swiglu, faster moe gemm * Faster rope * ISQ fixes * Clippy * First stab at harmony * Support builtin tools * Add streaming * Reasoning * Fix edge case * finally fast * A bit faster * Slight optimizations * metal build * Metal confirmed * Wire the final things up * Cleanup * Add examples * Clippy
58 lines
1.7 KiB
Python
58 lines
1.7 KiB
Python
from openai import OpenAI
|
|
import httpx
|
|
import textwrap
|
|
import json
|
|
|
|
|
|
def log_response(response: httpx.Response):
|
|
request = response.request
|
|
print(f"Request: {request.method} {request.url}")
|
|
print(" Headers:")
|
|
for key, value in request.headers.items():
|
|
if key.lower() == "authorization":
|
|
value = "[...]"
|
|
if key.lower() == "cookie":
|
|
value = value.split("=")[0] + "=..."
|
|
print(f" {key}: {value}")
|
|
print(" Body:")
|
|
try:
|
|
request_body = json.loads(request.content)
|
|
print(textwrap.indent(json.dumps(request_body, indent=2), " "))
|
|
except json.JSONDecodeError:
|
|
print(textwrap.indent(request.content.decode(), " "))
|
|
print(f"Response: status_code={response.status_code}")
|
|
print(" Headers:")
|
|
for key, value in response.headers.items():
|
|
if key.lower() == "set-cookie":
|
|
value = value.split("=")[0] + "=..."
|
|
print(f" {key}: {value}")
|
|
|
|
|
|
client = OpenAI(api_key="foobar", base_url="http://localhost:1234/v1/")
|
|
|
|
# Enable this to log requests and responses
|
|
# client._client = httpx.Client(
|
|
# event_hooks={"request": [print], "response": [log_response]}
|
|
# )
|
|
|
|
messages = []
|
|
prompt = input("Enter system prompt >>> ")
|
|
if len(prompt) > 0:
|
|
messages.append({"role": "system", "content": prompt})
|
|
|
|
|
|
while True:
|
|
prompt = input(">>> ")
|
|
messages.append({"role": "user", "content": prompt})
|
|
completion = client.chat.completions.create(
|
|
model="default",
|
|
messages=messages,
|
|
max_tokens=256,
|
|
frequency_penalty=1.0,
|
|
top_p=0.1,
|
|
temperature=0,
|
|
)
|
|
resp = completion.choices[0].message.content
|
|
print(completion.choices[0].message)
|
|
messages.append({"role": "assistant", "content": resp})
|