d746008e1f
- Created entrypoint-self-terminate.sh wrapper script - Updates entrypoint-generic.sh to be called by wrapper - Modified Dockerfile.runpod to use self-terminate entrypoint - Adds automatic pod termination via runpodctl after training completes - Prevents infinite restart loops and wasted GPU credits - Saves ~96% cost per training run ($4.59 per run) Implements pod self-termination using RUNPOD_POD_ID environment variable. Training exits with code 0 → runpodctl remove pod → immediate shutdown. Co-Authored-By: Claude <noreply@anthropic.com>
32 lines
514 B
TOML
32 lines
514 B
TOML
[workspace]
|
|
|
|
[package]
|
|
name = "runpod-debug"
|
|
version = "0.1.0"
|
|
edition = "2021"
|
|
|
|
[[bin]]
|
|
name = "test1_hello"
|
|
path = "test1_hello.rs"
|
|
|
|
[[bin]]
|
|
name = "test2_cuda_check"
|
|
path = "test2_cuda_check.rs"
|
|
|
|
[[bin]]
|
|
name = "test3_candle_device"
|
|
path = "test3_candle_device.rs"
|
|
|
|
[[bin]]
|
|
name = "test4_parquet_read"
|
|
path = "test4_parquet_read.rs"
|
|
|
|
[[bin]]
|
|
name = "test5_tft_minimal"
|
|
path = "test5_tft_minimal.rs"
|
|
|
|
[dependencies]
|
|
candle-core = { version = "0.8.0", features = ["cuda"] }
|
|
candle-nn = "0.8.0"
|
|
parquet = "53.3.0"
|