HK
Heykuki News
Top
New
Best
Ask
Show
Jobs
Toggle theme
Top
New
Best
Ask
Show
Jobs
Request
1.
▲
Why LLM decode is memory-bound, not compute-bound
github.com/harshuljain13
discuss
a month ago
harshuljain13
5 points
2.
▲
Free LLM inference handbook: 100 engineers cloned it in week 1
github.com/harshuljain13
discuss
16 days ago
harshuljain13
2 points