pullrequests Search Results · bucket language:JavaScript language:JavaScript language:HTML language:JavaScript language:Python
Filter by
984k results
Denver-Dietz
DavidStinson-GAWhat does this PR do?
In Bot Mode a bot s chat is a session tile and the primary selection is empty. The preview rail picks its profile bucket
from the primary runtime (railScopeForActiveSession ...
area/profiles
area/sessions
comp/desktop
P2
type/bug
PuntoyComaTech
... the batch-size buckets as:
max_bs = min(self.config.max_num_seqs, 512)
self.graph_bs = [1, 2, 4, 8] + list(range(16, max_bs + 1, 16))
which leaves out max_bs itself unless it is a multiple of 16 ...
mohan-zeyu
PolarisCzh
...
Summary
MiniMax-H3 on a 4x8 Galaxy served every request by padding the packed sequence to one of 26 bucket rungs and warming
each rung at start-up, because every op in the DiT block keyed its program ...
feat
pr-complexity:high
pr-priority:p2
pr-risk:high
rouzbehTT
Seya-prog
Display
🎯 P1 candidate
REDIS
security
🧪 tests
hangy