mirror of
https://github.com/qdrant/qdrant.git
synced 2026-07-23 11:11:00 -05:00
Add GPU support into Dockerfile (#5584)
* gpu hnsw
add gpu indexing flag
add gpu vector storage time measurement
add chmod flag
build hnsw using gpu
scoring speedup
move gl_GlobalInvocationID to mains
glslc with o flag
fix tests
use gpu atomics instead of multiple runs
enable atomics
add timers
profile search
let shader work while points collection
use generations for visited flags
add gpu init timer
avoid entries download
remove gpu call timers for a while
rename to combined graph builder
move gpu graph builder
restore levels in link access
restore links_map
add gpu start condition
use graph builder links memory
remove mut's
list point ids before processing
download-upload links using methods only
cpu graph builder as separate struct
add cpu threads count
parallel cpu build
single threaded cpu preprocess
try to fix glove accuracy
unsafe Send and Sync for gpu builder
copy graph layers builder instead of moving
remove obsolete mut
fix build
move builders to arc
fix bfb deadlock
move uneccessary clear
run cpu and gpu in separate threads
many vectors storage buffers
debug gpu vector storage
fix vector storage upload bug
add cpu ful graph build
don't use non-ready links for point
try to resolve conflicts while upsert
add indexing unit test for measurements
add test
utilize cpu more efficient
dont clear bhaep
debug gpu runs
try to use vec4 instead of mat4
dump scores count
estimate gpu usage
print usage per run
start using working groups
build shaders for vulkan v1.3
start shaders subgroup
vk instance version 1.3
subgroup vector storage
fix test
nearest heap
nearest heap test
are you happy fmt
add assert to nearest heap test
are you happy fmt
gpu visited flags
start candidates heap
candidates heap push
debug nearest heap
remove subgroupExclusiveMin
fix build
are you happy clippy
remove links dependency from nearest heap
provide input count to nearest test
are you happy fmt
provide ef to shader
are you happy fmt
get subgroup size
move compiled shaders
are you happy fmt
fix workgroups count for vector storage compute test
return true subgroup size
do nearest heap on gpu with partial sorting
remove tmp shader
unite scores and indices
are you happy fmt
gpu nearest sorting
are you happy fmt
fix nearest heap test
links test with subgroups
gpu candidates start
fix candidates sorting
are you happy fmt
fix candidates test on m1 chip
move obsolete and test shaders
start new gpu search context
search context test
fix links uploading
debug hnsw searh on level test
fix gpu hnsw search on level test
move test initialization to separate function
gpu greedy search shader test
test heuristic shader
gpu greedy search test
gpu test heuristic
move greedy search into searcher
start insertion shader
find hnsw patch on gpu
fix gpu patches test
start gpu graph builder
equivalency test
fix layers check
add timers
are you happy fmt
quality test and fix multithreaded bug
debug tests
are you happy fmt
fix levels count and clear links
fix equivalency test
remove obsolete solution
trivial gpu indexing integration
gpu config and skip conflicts for large hnsw
glsl generic vector storage element type
gpu generic vector storage
enable vulkan features for f16 and u8
force_half_precision option
add force f16 test
fix u8 and f16 unit tests
apply generic shaders in hnsw construction
remove conflicts check; start cpu utilization
cpu prebuild
upload first point links to gpu
mark all points in cpu graph as ready
multithreaded cpu and gpu
fix equivalency test
remove cpu links copy
parallel patches clearing
fix multithreaded env
external layers source
more logs to debug cpu+gpu syncronization
clear gpu processed points count
remove some temp logs
fix cpu stop condition bug
new insert vector shader
greedy search returns only ids
download whole layer links
apply new links on gpu directly
update win shader script
parallel links loading
provide memory amount as setting and estimate groups count
start bq
gpu bq test
fix tests
shaders invocations refactor
revert max groups settings
gix build after rebase
fix bug after rebase
upload links to gpu in cpu thread
fix greedy search iteration
atomic checker for conflicts
dump graph changes for debugging
move iterator to separate file
start combined builder refactor
start cpu builder as separate struct
separate gpu and cpu construction
fix tests
fix atomics count bug
upload links to gpu as separate fn
glue cpu and gpu
gpu thread
link points on cpu while gpu is busy
fix gpu bq scoring test
use xor instead of calc it
reallocate with less groups if not enough gpu memory
update compiled shaders
don't use llvm gpu emulator
debug panic if no gpu
remove tmp debug dumping
dockerfile for gpu
customize candidates count
fix gpu storage size
runtime shader compilation
dim as define
nearest heap params as macro
candidates and links capacities as macro
parallel bitonic sort
use bubble sort too
nearest heap as shared
limited shared candidates heap
combine buble and bitonic sorts
one-argumented similarity
cache vector for scoring
dont check candidates overflow
do greedy before search
visited hashtable
Revert "visited hashtable"
This reverts commit 7540d04d3859d02f17908c874927d18076f3eb8e.
use less flushes
bulk sum calculation
Revert "bulk sum calculation"
This reverts commit 6ef78ceb8d6ba7d9bf2077804548df162052c749.
load vector in one read
Revert "load vector in one read"
This reverts commit ea980d0399b90f44638590d40fdbfb1d6ffa9504.
fix build after rebase
fix build after rebase
sq support
simplify bq uploading using constructed quantization
metrics
alignment depends on subgroup size
are you happy fmt
exact flag
use lazy static for device access
remove prints
test reallocation factor
visited flags capacity as a compile time constant
build gpu hnsw for payload blocks
add dynamically sized subgroup size support
fix build
update rust version for nvidia docker
dynamically sized subgroups
start device filter
test device filter
are you happy clippy
devices manager
provide device instead of flag, better locking
partial cpu permit release
free cpus when gpu enabled
use cpu is waiting is disabled
create device only when gpu is enabled
cpu permit release all cases
parallel indices count
provide queue index
small refactor of shader builder
are you happy fmt
quantization params as separate struct
pq refactor
fmt
remove upload_mapped_ptr from gpu buffer
refactor gpu buffer
check buffer range
buffer refactor
refactor pipeline
move shader compiler to instance
refactor context
more refactor
no unwraps in gpu crate
clippy
apply pr changes
are you happy fmt
dont use shaderc in segment
more gpu tests
pq bq tests
provide bq option
fix bq for small dim
bind pq buffers
pq more complex test
cover all storage types by tests
test multi and vectors as iterator
multivectors upload data
multivectors shader
fix multivector tests
refactor shader builder
move storage tests into separate file
move quantization to separate file
refactor gpu vector storage creation
refactor gpu quantization api
dont convert to float when unnecessary
more comments
small upload vectors refactor
fix build after rebase
fix tests after rebase
different vk queue priorities capacity
vectors upload stopper
amd dockerfile
fix build after rebase
parent ec4d42e7f6
author Ivan Pleshkov <pleshkov.ivan@gmail.com> 1692111338 +0200
committer Ivan Pleshkov <pleshkov.ivan@gmail.com> 1732698560 +0100
gpu hnsw
add gpu indexing flag
add gpu vector storage time measurement
add chmod flag
build hnsw using gpu
scoring speedup
move gl_GlobalInvocationID to mains
glslc with o flag
fix tests
use gpu atomics instead of multiple runs
enable atomics
add timers
profile search
let shader work while points collection
use generations for visited flags
add gpu init timer
avoid entries download
remove gpu call timers for a while
rename to combined graph builder
move gpu graph builder
restore levels in link access
restore links_map
add gpu start condition
use graph builder links memory
remove mut's
list point ids before processing
download-upload links using methods only
cpu graph builder as separate struct
add cpu threads count
parallel cpu build
single threaded cpu preprocess
try to fix glove accuracy
unsafe Send and Sync for gpu builder
copy graph layers builder instead of moving
remove obsolete mut
fix build
move builders to arc
fix bfb deadlock
move uneccessary clear
run cpu and gpu in separate threads
many vectors storage buffers
debug gpu vector storage
fix vector storage upload bug
add cpu ful graph build
don't use non-ready links for point
try to resolve conflicts while upsert
add indexing unit test for measurements
add test
utilize cpu more efficient
dont clear bhaep
debug gpu runs
try to use vec4 instead of mat4
dump scores count
estimate gpu usage
print usage per run
start using working groups
build shaders for vulkan v1.3
start shaders subgroup
vk instance version 1.3
subgroup vector storage
fix test
nearest heap
nearest heap test
are you happy fmt
add assert to nearest heap test
are you happy fmt
gpu visited flags
start candidates heap
candidates heap push
debug nearest heap
remove subgroupExclusiveMin
fix build
are you happy clippy
remove links dependency from nearest heap
provide input count to nearest test
are you happy fmt
provide ef to shader
are you happy fmt
get subgroup size
move compiled shaders
are you happy fmt
fix workgroups count for vector storage compute test
return true subgroup size
do nearest heap on gpu with partial sorting
remove tmp shader
unite scores and indices
are you happy fmt
gpu nearest sorting
are you happy fmt
fix nearest heap test
links test with subgroups
gpu candidates start
fix candidates sorting
are you happy fmt
fix candidates test on m1 chip
move obsolete and test shaders
start new gpu search context
search context test
fix links uploading
debug hnsw searh on level test
fix gpu hnsw search on level test
move test initialization to separate function
gpu greedy search shader test
test heuristic shader
gpu greedy search test
gpu test heuristic
move greedy search into searcher
start insertion shader
find hnsw patch on gpu
fix gpu patches test
start gpu graph builder
equivalency test
fix layers check
add timers
are you happy fmt
quality test and fix multithreaded bug
debug tests
are you happy fmt
fix levels count and clear links
fix equivalency test
remove obsolete solution
trivial gpu indexing integration
gpu config and skip conflicts for large hnsw
glsl generic vector storage element type
gpu generic vector storage
enable vulkan features for f16 and u8
force_half_precision option
add force f16 test
fix u8 and f16 unit tests
apply generic shaders in hnsw construction
remove conflicts check; start cpu utilization
cpu prebuild
upload first point links to gpu
mark all points in cpu graph as ready
multithreaded cpu and gpu
fix equivalency test
remove cpu links copy
parallel patches clearing
fix multithreaded env
external layers source
more logs to debug cpu+gpu syncronization
clear gpu processed points count
remove some temp logs
fix cpu stop condition bug
new insert vector shader
greedy search returns only ids
download whole layer links
apply new links on gpu directly
update win shader script
parallel links loading
provide memory amount as setting and estimate groups count
start bq
gpu bq test
fix tests
shaders invocations refactor
revert max groups settings
gix build after rebase
fix bug after rebase
upload links to gpu in cpu thread
fix greedy search iteration
atomic checker for conflicts
dump graph changes for debugging
move iterator to separate file
start combined builder refactor
start cpu builder as separate struct
separate gpu and cpu construction
fix tests
fix atomics count bug
upload links to gpu as separate fn
glue cpu and gpu
gpu thread
link points on cpu while gpu is busy
fix gpu bq scoring test
use xor instead of calc it
reallocate with less groups if not enough gpu memory
update compiled shaders
don't use llvm gpu emulator
debug panic if no gpu
remove tmp debug dumping
dockerfile for gpu
customize candidates count
fix gpu storage size
runtime shader compilation
dim as define
nearest heap params as macro
candidates and links capacities as macro
parallel bitonic sort
use bubble sort too
nearest heap as shared
limited shared candidates heap
combine buble and bitonic sorts
one-argumented similarity
cache vector for scoring
dont check candidates overflow
do greedy before search
visited hashtable
Revert "visited hashtable"
This reverts commit 7540d04d3859d02f17908c874927d18076f3eb8e.
use less flushes
bulk sum calculation
Revert "bulk sum calculation"
This reverts commit 6ef78ceb8d6ba7d9bf2077804548df162052c749.
load vector in one read
Revert "load vector in one read"
This reverts commit ea980d0399b90f44638590d40fdbfb1d6ffa9504.
fix build after rebase
fix build after rebase
sq support
simplify bq uploading using constructed quantization
metrics
alignment depends on subgroup size
are you happy fmt
exact flag
use lazy static for device access
remove prints
test reallocation factor
visited flags capacity as a compile time constant
build gpu hnsw for payload blocks
add dynamically sized subgroup size support
fix build
update rust version for nvidia docker
dynamically sized subgroups
start device filter
test device filter
are you happy clippy
devices manager
provide device instead of flag, better locking
partial cpu permit release
free cpus when gpu enabled
use cpu is waiting is disabled
create device only when gpu is enabled
cpu permit release all cases
parallel indices count
provide queue index
small refactor of shader builder
are you happy fmt
quantization params as separate struct
pq refactor
fmt
remove upload_mapped_ptr from gpu buffer
refactor gpu buffer
check buffer range
buffer refactor
refactor pipeline
move shader compiler to instance
refactor context
more refactor
no unwraps in gpu crate
clippy
apply pr changes
are you happy fmt
dont use shaderc in segment
more gpu tests
pq bq tests
provide bq option
fix bq for small dim
bind pq buffers
pq more complex test
cover all storage types by tests
test multi and vectors as iterator
multivectors upload data
multivectors shader
fix multivector tests
refactor shader builder
move storage tests into separate file
move quantization to separate file
refactor gpu vector storage creation
refactor gpu quantization api
dont convert to float when unnecessary
more comments
small upload vectors refactor
fix build after rebase
fix tests after rebase
different vk queue priorities capacity
experiment with heaps
reverse candidates heap
scan only half of candidates
avoid heap code duplication
call subgroup elect inside bheap
united nearest and candidates heaps
remove cands and nearest heaps shaders
fix tests
start linear implementation
remove nearest and candidates entities
visited flags with id remap
simplify cpu side
move hnsw search shader into tests
simplify
simplify gpu links
test visited flags remap
remove GpuSearchContextGroupAllocation
stopper and allow integrated flag
add timeout comment
refactor batched points
refactor links and device manager
are you happy clippy
fix build after rebase
fix build after rebase
remove temp files
create gpu vectors in segment constructor
clean up
clean up
refactor gpu feature
refactor gpu construction in hnsw.rs
provide gpu device
remove pub
simplify main graph
renames
telemetry and settings refactor
update cargo lock
remove env_logger from deps
update openapi
gpu hnsw unit test
rename test
log device name while indexing
* are you happy clippy
* are you happy clippy
* dockerfile with amd and nvidia gpu support
* add gpu arg to stages
* clear after rebase
* Apply suggestions from code review
Co-authored-by: Roman Titov <ffuugoo@users.noreply.github.com>
* review remarks
* fix CI
* cnahge arg to env
---------
Co-authored-by: Roman Titov <ffuugoo@users.noreply.github.com>
This commit is contained in:
Ivan Pleshkov
2
Cargo.lock
generated
2
Cargo.lock
generated
@@ -2413,7 +2413,7 @@ checksum = "d2fabcfbdc87f4758337ca535fb41a6d701b65693ce38287d856d1674551ec9b"
|
||||
|
||||
[[package]]
|
||||
name = "gpu"
|
||||
version = "0.0.1"
|
||||
version = "0.1.0"
|
||||
dependencies = [
|
||||
"ash",
|
||||
"gpu-allocator",
|
||||
|
||||
51
Dockerfile
51
Dockerfile
@@ -1,3 +1,8 @@
|
||||
# Enable GPU support.
|
||||
# This option can be set to `nvidia` or `amd` to enable GPU support.
|
||||
# This option is defined here because it is used in `FROM` instructions.
|
||||
ARG GPU
|
||||
|
||||
# Cross-compiling using Docker multi-platform builds/images and `xx`.
|
||||
#
|
||||
# https://docs.docker.com/build/building/multi-platform/
|
||||
@@ -76,6 +81,9 @@ ARG RUSTFLAGS
|
||||
# Select linker (e.g., `mold`, `lld` or an empty string for the default linker)
|
||||
ARG LINKER=mold
|
||||
|
||||
# Enable GPU support
|
||||
ARG GPU
|
||||
|
||||
COPY --from=planner /qdrant/recipe.json recipe.json
|
||||
# `PKG_CONFIG=...` is a workaround for `xx-cargo` bug for crates using `pkg-config`!
|
||||
#
|
||||
@@ -84,7 +92,7 @@ COPY --from=planner /qdrant/recipe.json recipe.json
|
||||
RUN PKG_CONFIG="/usr/bin/$(xx-info)-pkg-config" \
|
||||
PATH="$PATH:/opt/mold/bin" \
|
||||
RUSTFLAGS="${LINKER:+-C link-arg=-fuse-ld=}$LINKER $RUSTFLAGS" \
|
||||
xx-cargo chef cook --profile $PROFILE ${FEATURES:+--features} $FEATURES --features=stacktrace --recipe-path recipe.json
|
||||
xx-cargo chef cook --profile $PROFILE ${FEATURES:+--features} $FEATURES --features=stacktrace ${GPU:+--features=gpu} --recipe-path recipe.json
|
||||
|
||||
COPY . .
|
||||
# Include git commit into Qdrant binary during build
|
||||
@@ -96,7 +104,7 @@ ARG GIT_COMMIT_ID
|
||||
RUN PKG_CONFIG="/usr/bin/$(xx-info)-pkg-config" \
|
||||
PATH="$PATH:/opt/mold/bin" \
|
||||
RUSTFLAGS="${LINKER:+-C link-arg=-fuse-ld=}$LINKER $RUSTFLAGS" \
|
||||
xx-cargo build --profile $PROFILE ${FEATURES:+--features} $FEATURES --features=stacktrace --bin qdrant \
|
||||
xx-cargo build --profile $PROFILE ${FEATURES:+--features} $FEATURES --features=stacktrace ${GPU:+--features=gpu} --bin qdrant \
|
||||
&& PROFILE_DIR=$(if [ "$PROFILE" = dev ]; then echo debug; else echo $PROFILE; fi) \
|
||||
&& mv target/$(xx-cargo --print-target-triple)/$PROFILE_DIR/qdrant /qdrant/qdrant
|
||||
|
||||
@@ -104,10 +112,47 @@ RUN PKG_CONFIG="/usr/bin/$(xx-info)-pkg-config" \
|
||||
RUN mkdir /static && STATIC_DIR=/static ./tools/sync-web-ui.sh
|
||||
|
||||
|
||||
FROM debian:12-slim AS qdrant
|
||||
# Dockerfile does not support conditional `FROM` directly.
|
||||
# To workaround this limitation, we use a multi-stage build with a different base images which have equal name to ARG value.
|
||||
|
||||
# Base image for Qdrant.
|
||||
FROM debian:12-slim AS qdrant-cpu
|
||||
|
||||
|
||||
# Base images for Qdrant with nvidia GPU support.
|
||||
FROM nvidia/opengl:1.0-glvnd-devel-ubuntu22.04 AS qdrant-gpu-nvidia
|
||||
# Set non-interactive mode for apt-get.
|
||||
ENV DEBIAN_FRONTEND=noninteractive
|
||||
# Set NVIDIA driver capabilities. By default, all capabilities are disabled.
|
||||
ENV NVIDIA_DRIVER_CAPABILITIES compute,graphics,utility
|
||||
# Copy Nvidia ICD loader file into the container.
|
||||
COPY --from=builder /qdrant/lib/gpu/nvidia_icd.json /etc/vulkan/icd.d/
|
||||
# Override maintainer label. Nvidia base image have it's own maintainer label.
|
||||
LABEL maintainer "Qdrant Team <info@qdrant.tech>"
|
||||
|
||||
|
||||
# Base images for Qdrant with amd GPU support.
|
||||
FROM rocm/dev-ubuntu-22.04 AS qdrant-gpu-amd
|
||||
# Set non-interactive mode for apt-get.
|
||||
ENV DEBIAN_FRONTEND=noninteractive
|
||||
# Override maintainer label. AMD base image have it's own maintainer label.
|
||||
LABEL maintainer "Qdrant Team <info@qdrant.tech>"
|
||||
|
||||
|
||||
FROM qdrant-${GPU:+gpu-}${GPU:-cpu} AS qdrant
|
||||
|
||||
RUN apt-get update
|
||||
|
||||
# Install GPU dependencies
|
||||
ARG GPU
|
||||
|
||||
RUN if [ -n "$GPU" ]; then \
|
||||
apt-get install -y \
|
||||
libvulkan1 \
|
||||
libvulkan-dev \
|
||||
vulkan-tools \
|
||||
; fi
|
||||
|
||||
# Install additional packages into the container.
|
||||
# E.g., the debugger of choice: gdb/gdbserver/lldb.
|
||||
ARG PACKAGES
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
[package]
|
||||
name = "gpu"
|
||||
version = "0.0.1"
|
||||
version = "0.1.0"
|
||||
authors = [
|
||||
"Qdrant Team <info@qdrant.tech>",
|
||||
]
|
||||
|
||||
7
lib/gpu/nvidia_icd.json
Normal file
7
lib/gpu/nvidia_icd.json
Normal file
@@ -0,0 +1,7 @@
|
||||
{
|
||||
"file_format_version" : "1.0.0",
|
||||
"ICD": {
|
||||
"library_path": "libGLX_nvidia.so.0",
|
||||
"api_version" : "1.3"
|
||||
}
|
||||
}
|
||||
Reference in New Issue
Block a user