Deepseek V4 (#23882)

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>
This commit is contained in:
Liangsheng Yin
2026-05-07 18:32:21 -07:00
committed by GitHub
co-authored by Baizhou Zhang Claude Opus 4.7 fzyzcjy ispobock Zhiqiang Xie yueming-yuan DarkSharpness Yuhao Yang yhyang201 yhyang201 Qiaolin Yu Ethan Su Mingyi Cheng Wan Yihao Wang
parent 55224fff08
commit 35870d55ac
154 changed files with 24970 additions and 759 deletions
+121
View File
@@ -0,0 +1,121 @@
"""H200 (FP8) x DeepSeek-V4-Flash.
Uses the FP8-repackaged repo (sgl-project/DeepSeek-V4-Flash-FP8) and
the SGLANG_DSV4_FP4_EXPERTS=0 env that the cookbook generator emits
for H200 FP8 cells. Covers Low-Latency, Balanced, Max-Throughput, 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, DSV4FlashAime25TestBase
MODEL = "sgl-project/DeepSeek-V4-Flash-FP8"
H200_FP8_ENV = {"SGLANG_DSV4_FP4_EXPERTS": "0"}
class TestH200Fp8FlashLowLatency(DSV4FlashAime25TestBase):
MODEL = MODEL
OTHER_ARGS = [
"--trust-remote-code",
"--tp",
"4",
"--speculative-algorithm",
"EAGLE",
"--speculative-num-steps",
"3",
"--speculative-eagle-topk",
"1",
"--speculative-num-draft-tokens",
"4",
]
EXTRA_ENV = dict(H200_FP8_ENV)
class TestH200Fp8FlashBalanced(DSV4FlashAime25TestBase):
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",
"--cuda-graph-max-bs",
"128",
"--max-running-requests",
"128",
"--deepep-config",
DEEPEP_LARGE_SMS_CONFIG,
]
EXTRA_ENV = {
**H200_FP8_ENV,
"SGLANG_DEEPEP_NUM_MAX_DISPATCH_TOKENS_PER_RANK": "256",
}
class TestH200Fp8FlashMaxThroughput(DSV4FlashAime25TestBase):
MODEL = MODEL
OTHER_ARGS = [
"--trust-remote-code",
"--tp",
"4",
"--dp",
"4",
"--enable-dp-attention",
"--moe-a2a-backend",
"deepep",
"--cuda-graph-max-bs",
"128",
"--max-running-requests",
"256",
"--deepep-config",
DEEPEP_LARGE_SMS_CONFIG,
]
EXTRA_ENV = {
**H200_FP8_ENV,
"SGLANG_DEEPEP_NUM_MAX_DISPATCH_TOKENS_PER_RANK": "256",
}
class TestH200Fp8FlashCP(DSV4FlashAime25TestBase):
MODEL = MODEL
OTHER_ARGS = [
"--trust-remote-code",
"--tp",
"4",
"--moe-a2a-backend",
"deepep",
"--enable-nsa-prefill-context-parallel",
"--nsa-prefill-cp-mode",
"round-robin-split",
"--chunked-prefill-size",
"16384",
"--mem-fraction-static",
"0.78",
"--max-running-requests",
"1024",
"--deepep-config",
DEEPEP_LARGE_SMS_CONFIG,
]
EXTRA_ENV = {
**H200_FP8_ENV,
"SGLANG_OPT_USE_JIT_INDEXER_METADATA": "1",
"SGLANG_DEEPEP_NUM_MAX_DISPATCH_TOKENS_PER_RANK": "1024",
}
if __name__ == "__main__":
unittest.main()