[Refactor] Refactor DeepEP dispatcher (#22822)

Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Co-authored-by: Cheng Wan <54331508+ch-wan@users.noreply.github.com>
This commit is contained in:
Артем Савкин
2026-05-18 04:36:42 +03:00
committed by GitHub
co-authored by gemini-code-assist[bot] Cheng Wan
parent 5147de26e4
commit a080358cac
30 changed files with 302 additions and 182 deletions
+2 -1
View File
@@ -192,6 +192,8 @@ class TestDeepseekV3W4Afp8DeepepAutoMtp(CustomTestCase):
"deepep",
"--deepep-mode",
"auto",
"--deepep-dispatcher-output-dtype",
"bf16",
"--dp",
"8",
"--enable-dp-attention",
@@ -215,7 +217,6 @@ class TestDeepseekV3W4Afp8DeepepAutoMtp(CustomTestCase):
other_args=other_args,
env={
**os.environ,
"SGLANG_DEEPEP_BF16_DISPATCH": "1",
"SGLANG_DEEPEP_NUM_MAX_DISPATCH_TOKENS_PER_RANK": "256",
},
)