Zhu Yi Lin 18302c8467 Revert "Add MagicMTP(block verify) and Triton optimization (#4443)" (#5380) ...

### What this PR does / why we need it?
#4443 introduces a precision issue in scenarios where MTP >= 3 + deepseek v3.1, and this pr reverts it

- vLLM version: release/v0.13.0
- vLLM main:
bc0a5a0c08

Signed-off-by: GDzhu01 <809721801@qq.com>

2025-12-26 15:06:13 +08:00

..

e2e

Revert "Add MagicMTP(block verify) and Triton optimization (#4443)" (#5380)

2025-12-26 15:06:13 +08:00

ut

[quantization] Add w8a16 quantization support (#4541)

2025-12-24 19:49:32 +08:00

__init__.py

[SpecDecode] Add spec decode support (#500)

2025-04-17 20:16:32 +08:00