v0.21.0rc3
Mirrored from vLLM releases for archival readability. Support the source by reading on the original site.
[MLA Attention Backend] Add TOKENSPEED_MLA backend for DSR1/Kimi K25 …
Mirrored from vLLM releases for archival readability. Support the source by reading on the original site.
[MLA Attention Backend] Add TOKENSPEED_MLA backend for DSR1/Kimi K25 …
Discussion (0)
Sign in to join the discussion. Free account, 30 seconds — email code or GitHub.
Sign in →No comments yet. Sign in and be the first to say something.