EngineX-Cambricon/enginex-mlu370-vllm
10
0
Fork 1
Code Issues Pull Requests Actions Projects Releases Wiki Activity
29 Commits 1 Branch 6 Tags
ebdc6fed03b2cf0198c305c5270e8caaa80ff8d8
Commit Graph

5 Commits

Author SHA1 Message Date
Chranos
ebdc6fed03 fix: pass lm_head to LogitsProcessor instead of calling forward() 
In vLLM v0.6.2, ParallelLMHead.forward() raises RuntimeError since
its weights should be used through LogitsProcessor.linear_method.apply().
Pass lm_head as first arg to LogitsProcessor which handles the
hidden_states -> logits projection internally.
 2026-02-06 14:21:14 +08:00
Chranos
4d0da98b9e testing dynamic register 2026-02-05 18:21:31 +08:00
Chranos
332e5f71a6 testing dynamic register 2026-02-05 18:02:59 +08:00
Chranos
6e38461af6 testing dynamic register 2026-02-05 17:11:09 +08:00
Chranos
b399840b8d testing dynamic register 2026-02-05 16:30:44 +08:00