Files
sglang/test/manual/dsv4/test_gb300_pro.py
T

127 lines
3.0 KiB
Python

"""GB300 x DeepSeek-V4-Pro.
Single-node TP=4 path. Note that GB300 Pro CP bumps
mem-fraction-static to 0.88 (1.6T weights at TP=4 on 273 GB don't
fit at the default 0.78). Covers Low-Latency, Balanced,
Max-Throughput, Context-Parallel (CP).
"""
import os
import sys
import unittest
sys.path.insert(0, os.path.dirname(os.path.abspath(__file__)))
from _common import DEEPEP_LARGE_SMS_CONFIG, DSV4ProAime25TestBase
MODEL = "deepseek-ai/DeepSeek-V4-Pro"
class TestGB300ProLowLatency(DSV4ProAime25TestBase):
MODEL = MODEL
OTHER_ARGS = [
"--trust-remote-code",
"--tp",
"4",
"--moe-runner-backend",
"flashinfer_mxfp4",
"--speculative-algorithm",
"EAGLE",
"--speculative-num-steps",
"3",
"--speculative-eagle-topk",
"1",
"--speculative-num-draft-tokens",
"4",
"--chunked-prefill-size",
"4096",
"--disable-flashinfer-autotune",
"--mem-fraction-static",
"0.88",
]
EXTRA_ENV = {}
class TestGB300ProBalanced(DSV4ProAime25TestBase):
MODEL = MODEL
OTHER_ARGS = [
"--trust-remote-code",
"--tp",
"4",
"--dp",
"4",
"--enable-dp-attention",
"--moe-a2a-backend",
"deepep",
"--speculative-algorithm",
"EAGLE",
"--speculative-num-steps",
"1",
"--speculative-eagle-topk",
"1",
"--speculative-num-draft-tokens",
"2",
"--mem-fraction-static",
"0.9",
"--cuda-graph-max-bs-decode",
"128",
"--max-running-requests",
"256",
"--deepep-config",
DEEPEP_LARGE_SMS_CONFIG,
]
EXTRA_ENV = {"SGLANG_DEEPEP_NUM_MAX_DISPATCH_TOKENS_PER_RANK": "256"}
class TestGB300ProMaxThroughput(DSV4ProAime25TestBase):
MODEL = MODEL
OTHER_ARGS = [
"--trust-remote-code",
"--tp",
"4",
"--dp",
"4",
"--enable-dp-attention",
"--moe-a2a-backend",
"deepep",
"--mem-fraction-static",
"0.9",
"--cuda-graph-max-bs-decode",
"128",
"--max-running-requests",
"256",
"--deepep-config",
DEEPEP_LARGE_SMS_CONFIG,
]
EXTRA_ENV = {"SGLANG_DEEPEP_NUM_MAX_DISPATCH_TOKENS_PER_RANK": "256"}
class TestGB300ProCP(DSV4ProAime25TestBase):
MODEL = MODEL
OTHER_ARGS = [
"--trust-remote-code",
"--tp",
"4",
"--moe-a2a-backend",
"deepep",
"--enable-dsa-prefill-context-parallel",
"--dsa-prefill-cp-mode",
"round-robin-split",
"--chunked-prefill-size",
"16384",
"--mem-fraction-static",
"0.88",
"--cuda-graph-max-bs-decode",
"256",
"--max-running-requests",
"256",
"--deepep-config",
DEEPEP_LARGE_SMS_CONFIG,
]
EXTRA_ENV = {
"SGLANG_DEEPEP_NUM_MAX_DISPATCH_TOKENS_PER_RANK": "256",
}
if __name__ == "__main__":
unittest.main()