Update README.md
Browse files
README.md
CHANGED
|
@@ -1,10 +1,24 @@
|
|
| 1 |
---
|
| 2 |
title: README
|
| 3 |
-
emoji:
|
| 4 |
colorFrom: green
|
| 5 |
colorTo: gray
|
| 6 |
sdk: static
|
| 7 |
pinned: false
|
| 8 |
---
|
| 9 |
|
| 10 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
title: README
|
| 3 |
+
emoji: 🚀
|
| 4 |
colorFrom: green
|
| 5 |
colorTo: gray
|
| 6 |
sdk: static
|
| 7 |
pinned: false
|
| 8 |
---
|
| 9 |
|
| 10 |
+
# Software Platform Team @ KETI
|
| 11 |
+
## Software Platform for Computing Systems
|
| 12 |
+
We design and optimize the full software stack for modern computing systems
|
| 13 |
+
through HW-SW co-design optimization — jointly evolving software abstractions
|
| 14 |
+
and hardware architectures to extract performance that neither side could deliver alone.
|
| 15 |
+
|
| 16 |
+
## Research Areas
|
| 17 |
+
### Runtime & Compiler
|
| 18 |
+
Custom compilers, runtime, and operator kernels for emerging computing architectures including Processing-In-Memory (PIM).
|
| 19 |
+
### LLM Serving Stack
|
| 20 |
+
Multi-client, multi-engine vLLM serving with traffic replay support.
|
| 21 |
+
### Full-System Simulation
|
| 22 |
+
End-to-end server-class LLM simulation for performance modeling and design space exploration.
|
| 23 |
+
### Profiling & Benchmarking
|
| 24 |
+
Workload characterization, kernel-level profiling, and bottleneck analysis across the stack.
|