Commit Graph

5 Commits

Author SHA1 Message Date
Chranos
c1b6f39a11 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 15:05:49 +08:00
Chranos
16353d5d2a testing dynamic register 2026-02-06 15:05:48 +08:00
Chranos
83c958a7c5 testing dynamic register 2026-02-06 15:05:48 +08:00
Chranos
9b84dd52be testing dynamic register 2026-02-06 15:05:48 +08:00
Chranos
2cb9f6ce1d testing dynamic register 2026-02-06 15:05:48 +08:00