Skip to content

Commit 5cc104b

Browse files
authored
fix: Change CMake variable for switch to knowhere-cuvs (milvus-io#40105)
issue: milvus-io#39883 Signed-off-by: Mickael Ide <[email protected]>
1 parent 259f910 commit 5cc104b

File tree

3 files changed

+3
-2
lines changed

3 files changed

+3
-2
lines changed

.gitignore

+1
Original file line numberDiff line numberDiff line change
@@ -29,6 +29,7 @@ docker-compose-devcontainer.yml.tmp
2929

3030
# Docker generated cache file
3131
.docker/
32+
.docker-gpu/
3233

3334
**/_artifacts/**
3435

README.md

+1-1
Original file line numberDiff line numberDiff line change
@@ -81,7 +81,7 @@ Milvus is designed to handle vector search at scale. It stores vectors, which ar
8181

8282

8383
**Support for Various Vector Index Types and Hardware Acceleration**
84-
* Milvus separates the system and core vector search engine, allowing it to support all major vector index types that are optimized for different scenarios, including HNSW, IVF, FLAT (brute-force), SCANN, and DiskANN, with [quantization-based](https://milvus.io/docs/index.md?tab=floating#IVFPQ) variations and [mmap](https://milvus.io/docs/mmap.md). Milvus optimizes vector search for advanced features such as [metadata filtering](https://milvus.io/docs/scalar_index.md#Scalar-Index) and [range search](https://milvus.io/docs/single-vector-search.md#Range-search). Additionally, Milvus implements hardware acceleration to enhance vector search performance and supports GPU indexing, such as NVIDIA's [CAGRA](https://github.com/rapidsai/raft).
84+
* Milvus separates the system and core vector search engine, allowing it to support all major vector index types that are optimized for different scenarios, including HNSW, IVF, FLAT (brute-force), SCANN, and DiskANN, with [quantization-based](https://milvus.io/docs/index.md?tab=floating#IVFPQ) variations and [mmap](https://milvus.io/docs/mmap.md). Milvus optimizes vector search for advanced features such as [metadata filtering](https://milvus.io/docs/scalar_index.md#Scalar-Index) and [range search](https://milvus.io/docs/single-vector-search.md#Range-search). Additionally, Milvus implements hardware acceleration to enhance vector search performance and supports GPU indexing, such as NVIDIA's [CAGRA](https://github.com/rapidsai/cuvs).
8585

8686

8787
**Flexible Multi-tenancy and Hot/Cold Storage**

internal/core/thirdparty/knowhere/CMakeLists.txt

+1-1
Original file line numberDiff line numberDiff line change
@@ -35,7 +35,7 @@ else ()
3535
endif()
3636

3737
if ( MILVUS_GPU_VERSION STREQUAL "ON" )
38-
set(WITH_RAFT ON CACHE BOOL "" FORCE )
38+
set(WITH_CUVS ON CACHE BOOL "" FORCE )
3939
endif ()
4040

4141
set( CMAKE_PREFIX_PATH ${CONAN_BOOST_ROOT} )

0 commit comments

Comments
 (0)