Gahow Wang
95eb61d639
tp_engine: rank-0 coordinator owns the scheduler and broadcasts per-token commands (Register/Prefill/Decode/Free) to worker rank threads; the sampled token always comes from rank 0, so it's correct for greedy and stochastic sampling. Serial single-request path (sufficient for the quality benchmark). --tp N selects it; TP=1 keeps the existing single-GPU Engine unchanged. Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
24 lines
596 B
TOML
24 lines
596 B
TOML
[package]
|
|
name = "xserv-server"
|
|
version.workspace = true
|
|
edition.workspace = true
|
|
|
|
[[bin]]
|
|
name = "xserv-server"
|
|
path = "src/main.rs"
|
|
|
|
[dependencies]
|
|
xserv-cuda = { path = "../xserv-cuda" }
|
|
xserv-tensor = { path = "../xserv-tensor" }
|
|
xserv-kernels = { path = "../xserv-kernels" }
|
|
xserv-model = { path = "../xserv-model" }
|
|
xserv-tokenizer = { path = "../xserv-tokenizer" }
|
|
xserv-distributed = { path = "../xserv-distributed" }
|
|
half.workspace = true
|
|
serde.workspace = true
|
|
serde_json.workspace = true
|
|
tokio.workspace = true
|
|
axum.workspace = true
|
|
uuid.workspace = true
|
|
tokio-stream.workspace = true
|