[Doc]: fix typos in various files (#24726)
Signed-off-by: Didier Durand <durand.didier@gmail.com>
This commit is contained in:
@@ -2659,7 +2659,7 @@ class GPUModelRunner(LoRAModelRunnerMixin, KVConnectorModelRunnerMixin):
|
||||
num_tokens += num_pad
|
||||
|
||||
# If cudagraph_mode.decode_mode() == FULL and
|
||||
# cudagraph_mode.seperate_routine(). This means that we are using
|
||||
# cudagraph_mode.separate_routine(). This means that we are using
|
||||
# different graphs and/or modes for mixed prefill-decode batches vs.
|
||||
# uniform decode batches. A uniform decode batch means that all
|
||||
# requests have identical query length, except a potential virtual
|
||||
|
||||
Reference in New Issue
Block a user