+6
35870d55ac
35870d55ac
Co-authored-by: Baizhou Zhang <sobereddiezhang@gmail.com> Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com> Co-authored-by: fzyzcjy <ch271828n@outlook.com> Co-authored-by: ispobock <ispobaoke@gmail.com> Co-authored-by: Zhiqiang Xie <xiezhq@stanford.edu> Co-authored-by: yueming-yuan <yym022502@gmail.com> Co-authored-by: DarkSharpness <2040703891@qq.com> Co-authored-by: Yuhao Yang <47235274+yhyang201@users.noreply.github.com> Co-authored-by: yhyang201 <yhyang201@users.noreply.github.com> Co-authored-by: yhyang201 <yhyang201@gmail.com> Co-authored-by: Qiaolin Yu <90088090+qiaolin-yu@users.noreply.github.com> Co-authored-by: Ethan (Yusheng) Su <11704492+yushengsu-thu@users.noreply.github.com> Co-authored-by: Mingyi <27337995+wisclmy0611@users.noreply.github.com> Co-authored-by: Cheng Wan <54331508+ch-wan@users.noreply.github.com> Co-authored-by: Yihao Wang <42559837+againstentropy@users.noreply.github.com>
78 lines
1.6 KiB
Python
78 lines
1.6 KiB
Python
"""H200 (FP4 / Marlin) x DeepSeek-V4-Pro.
|
|
|
|
The cookbook disables Context-Parallel for the H200 FP4 (Marlin)
|
|
hardware, so this file only covers Low-Latency, Balanced, and
|
|
Max-Throughput.
|
|
"""
|
|
|
|
import os
|
|
import sys
|
|
import unittest
|
|
|
|
sys.path.insert(0, os.path.dirname(os.path.abspath(__file__)))
|
|
from _common import DSV4ProAime25TestBase
|
|
|
|
MODEL = "deepseek-ai/DeepSeek-V4-Pro"
|
|
|
|
|
|
class TestH200Fp4ProLowLatency(DSV4ProAime25TestBase):
|
|
MODEL = MODEL
|
|
OTHER_ARGS = [
|
|
"--trust-remote-code",
|
|
"--tp",
|
|
"8",
|
|
"--moe-runner-backend",
|
|
"marlin",
|
|
"--speculative-algorithm",
|
|
"EAGLE",
|
|
"--speculative-num-steps",
|
|
"3",
|
|
"--speculative-eagle-topk",
|
|
"1",
|
|
"--speculative-num-draft-tokens",
|
|
"4",
|
|
"--mem-fraction-static",
|
|
"0.88",
|
|
]
|
|
EXTRA_ENV = {}
|
|
|
|
|
|
class TestH200Fp4ProBalanced(DSV4ProAime25TestBase):
|
|
MODEL = MODEL
|
|
OTHER_ARGS = [
|
|
"--trust-remote-code",
|
|
"--tp",
|
|
"8",
|
|
"--moe-runner-backend",
|
|
"marlin",
|
|
"--speculative-algorithm",
|
|
"EAGLE",
|
|
"--speculative-num-steps",
|
|
"1",
|
|
"--speculative-eagle-topk",
|
|
"1",
|
|
"--speculative-num-draft-tokens",
|
|
"2",
|
|
"--mem-fraction-static",
|
|
"0.88",
|
|
]
|
|
EXTRA_ENV = {}
|
|
|
|
|
|
class TestH200Fp4ProMaxThroughput(DSV4ProAime25TestBase):
|
|
MODEL = MODEL
|
|
OTHER_ARGS = [
|
|
"--trust-remote-code",
|
|
"--tp",
|
|
"8",
|
|
"--moe-runner-backend",
|
|
"marlin",
|
|
"--mem-fraction-static",
|
|
"0.88",
|
|
]
|
|
EXTRA_ENV = {}
|
|
|
|
|
|
if __name__ == "__main__":
|
|
unittest.main()
|