Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
3 changes: 3 additions & 0 deletions README.md
Original file line number Diff line number Diff line change
Expand Up @@ -5,6 +5,9 @@
</h2>
</div>

:fire: Go with us to enjoy Nvidia GTC happy hours [SGLang x RadixArk](https://luma.com/hgj595as)
:point_right: 03/17 06:30 PM PDT | San Jose, California

## About
**SiMM** is a high-performance, scalable Key-Value (KV) cache engine designed for LLM inference workloads. It addresses the critical bottlenecks in long-context prompts and multi-turn agent interactions by providing a dedicated, fast memory pool for KV cache storage.
Seamlessly integrated with leading inference engines like SGLang and vLLM, enabling offload and retrieve KV caches from SiMM, inference engines can bypass redundant prefill computations, significantly save GPU cycles and drastically reduce Time to First Token (TTFT). SiMM is already proven and validated in production environments.
Expand Down
4 changes: 2 additions & 2 deletions docs/faq.md
Original file line number Diff line number Diff line change
Expand Up @@ -5,8 +5,8 @@
SiMM built on Folly Codes with tag [v2025.07.07.00](https://github.com/facebook/folly/tree/v2025.07.07.00) defaultly, such release version had fmt lib related build issue, **so you need to patch the fix locally before SiMM build** :
- git issue : https://github.com/facebook/folly/issues/2468
- mr link : https://github.com/facebook/folly/commit/03ba79afc093424ba73ebe23c8b01a3c39b908ef
<div align="center">
<img src="docs/images/folly_v20250707_fmt_patch.png" alt="Folly Fmt build issue" width="70%" />
<div align="left">
<img src="images/folly_v20250707_fmt_patch.png" alt="Folly Fmt build issue" width="80%" />
</div>

### 1.2 Folly(liburing)
Expand Down
Loading