mirror of
https://github.com/Niko1221/Strata.git
synced 2026-11-07 06:15:58 -10:00
Niko1221
a9adfa5dad
Setup: the images question for qwen36 (GPU encoder on an NVIDIA card of 16 GB or more, the CPU encoder otherwise, AMD under Linux on the CPU; --vision gpu kept as asked with a note), the pinned mmproj (size and SHA-256) beside the GGUF, the vision section and --vision in the config; --parallel N is written as asked with what a slot costs, and the recommendation is said where every expert still fits. docs/QWEN36.md: pictures and several requests at once with the measurements.
49 lines
2.1 KiB
Python
49 lines
2.1 KiB
Python
"""serve/test_q36_config.py - what the server hands the Qwen3.6-35B-A3B engine (arch qwen35moe): the config's pictures
|
|
("vision" section -> --vision) and parallel requests ("parallel": N -> --batch N), as for Flash-Next's engine.
|
|
|
|
python -m unittest serve.test_q36_config
|
|
"""
|
|
from __future__ import annotations
|
|
|
|
import unittest
|
|
from unittest import mock
|
|
|
|
from serve.server import engine_args, parallel_args
|
|
|
|
|
|
def cfg(**kw):
|
|
base = {"arch": "qwen35moe", "exe": "strata", "args": ["--native", "/m/Qwen3.6-35B-A3B-UD-Q4_K_XL.gguf",
|
|
"--max-context", "32768", "--prefill", "auto", "--mtp", "2"]}
|
|
base.update(kw)
|
|
return base
|
|
|
|
|
|
class Q36Config(unittest.TestCase):
|
|
def test_parallel_becomes_batch(self):
|
|
a = engine_args(cfg(parallel=4))
|
|
self.assertEqual(a[a.index("--batch") + 1], "4")
|
|
self.assertNotIn("--batch", engine_args(cfg()))
|
|
self.assertNotIn("--batch", engine_args(cfg(parallel=1)))
|
|
|
|
def test_more_than_the_window_is_said(self):
|
|
with mock.patch("builtins.print") as pr:
|
|
a = engine_args(cfg(parallel=12))
|
|
self.assertEqual(a[a.index("--batch") + 1], "12") # the engine caps it at 8 and says so
|
|
self.assertTrue(any("at most 8" in str(c) for c in pr.call_args_list))
|
|
|
|
def test_a_vision_section_starts_the_engine_with_pictures(self):
|
|
v = {"exe": "strata-vision", "mmproj": "/m/mmproj-F16.gguf", "model": "/m/Qwen3.6-35B-A3B-UD-Q4_K_XL.gguf",
|
|
"gpu": False, "max_tokens": 300}
|
|
self.assertIn("--vision", engine_args(cfg(vision=v)))
|
|
self.assertIn("--vision", engine_args(cfg(vision=v, args=cfg()["args"] + ["--vision"])))
|
|
self.assertEqual(engine_args(cfg(vision=v, args=cfg()["args"] + ["--vision"])).count("--vision"), 1)
|
|
self.assertNotIn("--vision", engine_args(cfg()))
|
|
|
|
def test_an_explicit_batch_in_the_args_wins(self):
|
|
c = cfg(parallel=4, args=cfg()["args"] + ["--batch", "2"])
|
|
self.assertEqual(parallel_args(c, c["args"]), [])
|
|
|
|
|
|
if __name__ == "__main__":
|
|
unittest.main()
|