HK
Heykuki News
Top
New
Best
Ask
Show
Jobs
Toggle theme
Top
New
Best
Ask
Show
Jobs
Request
1.
▲
Show HN: KTransformers–236B Model and 1M Context LLM Inference on Local Machines
github.com/kvcache-ai
3 comments
2 years ago
sssummer
20 points
2.
▲
Show HN: KTransformers:671B DeepSeek-R1 on a Single Machine-286 tokens/s Prefill
github.com/kvcache-ai
discuss
a year ago
sssummer
14 points
3.
▲
Mooncake: A KVCache-Centric Disaggregated Architecture for LLM Serving
github.com/kvcache-ai
discuss
2 years ago
zinccat
13 points
4.
▲
Mooncake: A KVCache-centric Disaggregated Architecture for LLM Serving
github.com/kvcache-ai
discuss
a year ago
sarkory
8 points