Gahow Wang
453520d622
New xserv-distributed crate: hand-written NCCL FFI, TpContext (one rank per thread, bound to one GPU), and in-place BF16 AllReduce on the null stream so it orders naturally with the model's kernels. 2-GPU AllReduce test included. Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
30 lines
596 B
TOML
30 lines
596 B
TOML
[workspace]
|
|
resolver = "2"
|
|
members = [
|
|
"crates/xserv-cuda",
|
|
"crates/xserv-tensor",
|
|
"crates/xserv-kernels",
|
|
"crates/xserv-model",
|
|
"crates/xserv-tokenizer",
|
|
"crates/xserv-server",
|
|
"crates/xserv-distributed",
|
|
]
|
|
|
|
[workspace.package]
|
|
version = "0.1.0"
|
|
edition = "2024"
|
|
license = "MIT"
|
|
|
|
[workspace.dependencies]
|
|
half = "2"
|
|
smallvec = "1"
|
|
serde = { version = "1", features = ["derive"] }
|
|
serde_json = "1"
|
|
safetensors = "0.5"
|
|
regex = "1"
|
|
tokio = { version = "1", features = ["full"] }
|
|
axum = "0.8"
|
|
uuid = { version = "1", features = ["v4"] }
|
|
tokio-stream = "0.1"
|
|
rand = "0.8"
|