Baizhou Zhang

icon indicating an email [email protected]

icon company MSCS@UCSD icon location La Jolla, USA icon location Novice of Building Systems

Results 82 comments of Baizhou Zhang

[Bug] H20 deepseek infer enable flashinfer mla hang

@lambert0312 @ProphetPeng Please try pulling the latest main branch, now `--enable-flashinfer-mla` and radix cache can be used together.

[Fix] Fix bugs and refactor codes in lora for better scalability.

LGTM