sgl-project--sglang/python/sglang/srt/mem_cache/storage/nixl/nixl.config.toml.sample

################################################################################
# IMPORTANT
# 1. to enable a plugin, add "active = true" in the corresponding section
# 2. the configs inside plugin.posix (i.e., use_aio, use_uring, use_posix_aio)
#    are mutually exclusive
################################################################################


########################################
# GLOBAL NIXL HICACHE SETTINGS
########################################

# Open FILE-backend cache files with O_DIRECT when supported.
use_direct_io = true

# Built-in background cleaner for FILE-backed L3 storage. Set to false when an
# external cleaner is responsible for eviction. OBJ plugins ignore this.
l3_cleaner_enabled = true

# Background cleaner watermarks for FILE-backed L3 storage. OBJ plugins ignore these.
l3_cleaner_high_watermark = 80.0
l3_cleaner_low_watermark = 70.0


########################################
# POSIX FILE SYSTEM BACKEND
########################################
[plugin.posix]
# Configuration for the POSIX file-based backend.
#
# The supported backends include:
# 1. AIO (`use_aio = "true"`)
# 2. io_uring (`use_uring = "true"`)
# 3. POSIX AIO (`use_posix_aio = "true"`)
#
# If not specified, NIXL will automatically detect and use available backends based on the following default priority: AIO > io_uring > POSIX AIO

# Enable Linux io_uring for async I/O (recommended if supported)
use_uring = "true"

# Enable POSIX AIO (alternative async I/O mechanism)
# use_posix_aio = "true"

# Enable generic AIO
# use_aio = "true"

# Whether this plugin is eligible for selection
active = true


########################################
# NVIDIA GDS (GPUDirect Storage) BACKEND
########################################
[plugin.gds]
# Configuration for NVIDIA GPUDirect Storage
# Requires compatible GPU, driver, and filesystem support

# Number of requests per batch, default: 128
batch_pool_size = 128

# Maximum number of requests issued at once, default: 128
batch_limit = 128

# Maximum size of a single request (bytes), default: 16MB
max_request_size = 16777216  # 16 MB


########################################
# MULTI-THREADED GDS BACKEND
########################################
[plugin.gds_mt]
# Multi-threaded variant of the GDS backend

# Number of worker threads, default: 4
thread_count = 4


########################################
# 3FS (THIRD-PARTY FILE SYSTEM) BACKEND
########################################
[plugin.3fs]
# Configuration for 3FS backend
# Requires the 3FS library to be installed and mounted

# Mount point of the 3FS filesystem
mount_point = "/mnt/3fs"

# Memory configuration mode:
#   dram     - use DRAM
#   dram_zc  - DRAM with zero-copy
#   auto     - let backend decide
mem_config = "dram"

# Size of the I/O pool
# Valid range: [2^6, 2^20]
iopool_size = 64


########################################
# OBJECT STORAGE BACKEND (S3 / COMPATIBLE)
########################################
[plugin.obj]
# Object storage backend (e.g., S3-compatible services)

# Number of client worker threads, default: 4
num_threads = 4

# Override endpoint (useful for non-AWS S3 services)
endpoint_override = ""

# Connection scheme: http or https, default: http
scheme = "http"

# Cloud region (if applicable)
region = ""

# Request checksum behavior:
#   required, supported
req_checksum = "required"

# Custom CA bundle path (if needed)
ca_bundle = ""

# Credentials
access_key = ""
secrete_key = ""
session_token = ""

# Use virtual-hosted-style addressing (true/false), default: true
use_virtual_addressing = "true"

# Default bucket name
bucket = ""