A Survey of Quantization Methods for Efficient Neural Network Inference

Signed-off-by: Zhao Junwang <zhjwpku@gmail.com>
zhjwpku · Feb 27, 2024 · 3905fa3 · 3905fa3
1 parent 038043d
commit 3905fa3
Show file tree

Hide file tree

Showing 4 changed files with 8 additions and 1 deletion.
diff --git a/src/SUMMARY.md b/src/SUMMARY.md
@@ -33,6 +33,7 @@
   - [cdc](./databases/cdc/README.md)
     - [dblog](./databases/cdc/dblog.md)
   - [rum conjecture](./databases/rum.md)
+  - [vector db](./databases/vectordb/README.md)
 - [datalayout](./datalayout/README.md)
   - [cstore](./datalayout/c-store.md)
   - [cstore compression](./datalayout/c-store-compression.md)
@@ -78,4 +79,4 @@
   - [kv store](./storage/kv/README.md)
     - [dynamo](./storage/kv/dynamo.md)
   - [kudu](./storage/kudu.md)
-  - [bluestore](./storage/bluestore.md)
+  - [bluestore](./storage/bluestore.md)
diff --git a/src/assets/pdfs/A_Survey_of_Quantization_Methods_for_Efficient_Neural_Network_Inference.pdf b/src/assets/pdfs/A_Survey_of_Quantization_Methods_for_Efficient_Neural_Network_Inference.pdf
diff --git a/src/databases/README.md b/src/databases/README.md
@@ -23,6 +23,7 @@
 - **[Change Data Capture](cdc/index.html)**
   - **[DBLog: AWatermark Based Change-Data-Capture Framework][dblog]**
 - **[Designing Access Methods: The RUM Conjecture][rum]**
+- **[VectorDB](vectordb/index.html)**
 
 #### Optional readings
 

diff --git a/src/databases/vectordb/README.md b/src/databases/vectordb/README.md
@@ -0,0 +1,5 @@
+## vector db
+
+### Quantization
+
+- [A Survey of Quantization Methods for Efficient Neural Network Inference](/assets/pdfs/A_Survey_of_Quantization_Methods_for_Efficient_Neural_Network_Inference.pdf)