We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
There was an error while loading. Please reload this page.
1 parent 13889f5 commit 59653f1Copy full SHA for 59653f1
tensorrt_llm/_torch/modules/fused_moe/fused_moe_trtllm_gen.py
@@ -191,9 +191,9 @@ def enable_alltoall(self):
191
192
@cached_property
193
def moe_alltoall_backend(self):
194
- # "MnnvlLatency" (default) or "MnnvlThroughput"
+ # "mnnvllatency" (default) or "mnnvlthroughput"
195
return os.environ.get("TRTLLM_MOE_ALLTOALL_BACKEND",
196
- "MnnvlLatency").strip().lower()
+ "mnnvllatency").strip().lower()
197
198
def _check_configs(self):
199
assert self.has_deepseek_fp8_block_scales \
0 commit comments