Error for Lesson 7 - LoRAX

Short Course Q&A Efficiently Serving LLMs
1

All lessons up to Lesson 7 worked fine.
But, in this lesson, when running step “Prefill vs Decode (KV Cache)” I get the error “JSONDecodeError: Expecting value: line 1 column 1 (char 0)”

---------------------------------------------------------------------------
JSONDecodeError                           Traceback (most recent call last)
File /usr/local/lib/python3.11/site-packages/requests/models.py:971, in Response.json(self, **kwargs)
    970 try:
--> 971     return complexjson.loads(self.text, **kwargs)
    972 except JSONDecodeError as e:
    973     # Catch JSON-related errors and raise as requests.JSONDecodeError
    974     # This aliases json.JSONDecodeError and simplejson.JSONDecodeError

File /usr/local/lib/python3.11/json/__init__.py:346, in loads(s, cls, object_hook, parse_float, parse_int, parse_constant, object_pairs_hook, **kw)
    343 if (cls is None and object_hook is None and
    344         parse_int is None and parse_float is None and
    345         parse_constant is None and object_pairs_hook is None and not kw):
--> 346     return _default_decoder.decode(s)
    347 if cls is None:

File /usr/local/lib/python3.11/json/decoder.py:337, in JSONDecoder.decode(self, s, _w)
    333 """Return the Python representation of ``s`` (a ``str`` instance
    334 containing a JSON document).
    335 
    336 """
--> 337 obj, end = self.raw_decode(s, idx=_w(s, 0).end())
    338 end = _w(s, end).end()

File /usr/local/lib/python3.11/json/decoder.py:355, in JSONDecoder.raw_decode(self, s, idx)
    354 except StopIteration as err:
--> 355     raise JSONDecodeError("Expecting value", s, err.value) from None
    356 return obj, end

JSONDecodeError: Expecting value: line 1 column 1 (char 0)

During handling of the above exception, another exception occurred:

JSONDecodeError                           Traceback (most recent call last)
Cell In[14], line 2
      1 t0 = time.time()
----> 2 resp = client.generate("What is deep learning?", max_new_tokens=32)
      3 duration_s = time.time() - t0
      5 print(resp.generated_text)

File /usr/local/lib/python3.11/site-packages/lorax/client.py:182, in Client.generate(self, prompt, adapter_id, adapter_source, merged_adapters, api_token, do_sample, max_new_tokens, best_of, repetition_penalty, return_full_text, seed, stop_sequences, temperature, top_k, top_p, truncate, typical_p, watermark, response_format, decoder_input_details, details)
    173 resp = requests.post(
    174     self.base_url,
    175     json=request.dict(by_alias=True),
   (...)
    178     timeout=self.timeout,
    179 )
    181 # TODO: expose better error messages for 422 and similar errors
--> 182 payload = resp.json()
    183 if resp.status_code != 200:
    184     raise parse_error(resp.status_code, payload)

File /usr/local/lib/python3.11/site-packages/requests/models.py:975, in Response.json(self, **kwargs)
    971     return complexjson.loads(self.text, **kwargs)
    972 except JSONDecodeError as e:
    973     # Catch JSON-related errors and raise as requests.JSONDecodeError
    974     # This aliases json.JSONDecodeError and simplejson.JSONDecodeError
--> 975     raise RequestsJSONDecodeError(e.msg, e.doc, e.pos)

JSONDecodeError: Expecting value: line 1 column 1 (char 0)
2

Same error

1 Like