apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2026-04-23 00:17:25 +08:00
Code Issues Actions 19 Packages Projects Releases Wiki Activity

Split enable_mm (#7183)

Browse Source 
Co-authored-by: liuruian <liuruian@MacBook-Pro.local>
This commit is contained in:
K11OntheBoat
2026-04-08 11:25:41 +08:00
committed by GitHub
parent 8496ec71a6
commit bb48bcbaa2
33 changed files with 109 additions and 69 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tests/distributed/chunked_moe.py
+2 -1
View File
@@ -92,6 +92,7 @@ class MockFDConfig:
model_config = MockModelConfig()
cache_config = MockCacheConfig()
speculative_config = MockSpecaulativeConfig()
enable_mm_runtime = MockModelConfig.enable_mm
def get_max_chunk_tokens(self, mm_max_tokens_per_item=None):
return 8192
@@ -139,7 +140,7 @@ class TestChunkedMoE(unittest.TestCase):
model_runner.model_config = mock_model_config
model_runner.cache_config = mock_cache_config
model_runner.attn_backends = [MockAttentionBackend()]
model_runner.enable_mm = True
model_runner.enable_mm = mock_fd_config.enable_mm_runtime
model_runner.cudagraph_only_prefill = False
model_runner.use_cudagraph = False
model_runner.speculative_decoding = False