EngineX-Hygon/sglang
5
0
Fork 0
Code Issues Pull Requests Actions 7 Projects Releases Wiki Activity

[Fix] Add speculative_draft_model_revision to server_args (#5255)

Browse Source 
Signed-off-by: Devashish Lal <devashish@rivosinc.com>
This commit is contained in:
DevashishLal-CB
2025-09-05 04:45:46 -07:00
committed by GitHub
parent df97b31f37
commit 13705dae06
13 changed files with 68 additions and 45 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
test/srt/test_fa3.py
View File

@@ -146,7 +146,7 @@ class TestFlashAttention3SpeculativeDecode(BaseFlashAttentionTest):
"4",
"--speculative-algorithm",
"EAGLE3",
"--speculative-draft",
"--speculative-draft-model-path",
DEFAULT_MODEL_NAME_FOR_TEST_EAGLE3,
"--speculative-num-steps",
"3",
@@ -180,7 +180,7 @@ class TestFlashAttention3SpeculativeDecodeTopk(BaseFlashAttentionTest):
"4",
"--speculative-algorithm",
"EAGLE3",
"--speculative-draft",
"--speculative-draft-model-path",
DEFAULT_MODEL_NAME_FOR_TEST_EAGLE3,
"--speculative-num-steps",
"5",
@@ -212,7 +212,7 @@ class TestFlashAttention3MLASpeculativeDecode(BaseFlashAttentionTest):
"4",
"--speculative-algorithm",
"EAGLE",
"--speculative-draft",
"--speculative-draft-model-path",
DEFAULT_MODEL_NAME_FOR_TEST_MLA_NEXTN,
"--speculative-num-steps",
"3",
@@ -244,7 +244,7 @@ class TestFlashAttention3MLASpeculativeDecodeTopk(BaseFlashAttentionTest):
"4",
"--speculative-algorithm",
"EAGLE",
"--speculative-draft",
"--speculative-draft-model-path",
DEFAULT_MODEL_NAME_FOR_TEST_MLA_NEXTN,
"--speculative-num-steps",
"5",