Compare commits
2 Commits
main
...
1eef10afd9
| Author | SHA1 | Date | |
|---|---|---|---|
| 1eef10afd9 | |||
| 1b58bd8626 |
@@ -38,6 +38,46 @@ fn test_config(vocab: usize) -> Config {
|
||||
cfg
|
||||
}
|
||||
|
||||
/// Run `cfg`/`dcfg` as a 2-rank DDP job (the same launcher path as production) and
|
||||
/// return rank 0's (loss trace, final params on host, final `is_training()` flag).
|
||||
/// `cfg` carries the dropout prob; `dcfg` carries the loop knobs. Caller asserts.
|
||||
fn run_ddp2(
|
||||
cfg: Config,
|
||||
corpus: &Corpus,
|
||||
valid: Option<&Corpus>,
|
||||
dcfg: &DdpConfig,
|
||||
) -> (Vec<f32>, Vec<Vec<f32>>, bool) {
|
||||
let world = 2usize;
|
||||
let devices = [0u32, 1u32];
|
||||
let id = get_unique_id();
|
||||
let results: Vec<(Vec<f32>, Vec<Vec<f32>>, bool)> = std::thread::scope(|s| {
|
||||
let handles: Vec<_> = devices
|
||||
.iter()
|
||||
.enumerate()
|
||||
.map(|(rank, &dev)| {
|
||||
let dcfg = dcfg.clone();
|
||||
let corpus = &corpus;
|
||||
s.spawn(move || {
|
||||
let ctx = DdpContext::init(rank, world, id, dev);
|
||||
let device = Device::Cuda(dev);
|
||||
let model = build_model(cfg, device);
|
||||
// Only rank 0 holds the val corpus (mirrors launch()).
|
||||
let v = if rank == 0 { valid } else { None };
|
||||
let res = train_rank(&ctx, &model, device, corpus, v, &dcfg);
|
||||
let host = model
|
||||
.params()
|
||||
.iter()
|
||||
.map(|p| p.value().to_device(Device::Cpu).as_slice::<f32>().to_vec())
|
||||
.collect::<Vec<_>>();
|
||||
(res.losses, host, model.is_training())
|
||||
})
|
||||
})
|
||||
.collect();
|
||||
handles.into_iter().map(|h| h.join().unwrap()).collect()
|
||||
});
|
||||
results.into_iter().next().unwrap()
|
||||
}
|
||||
|
||||
// Single-GPU baseline: the SAME loop as the DDP rank but world=1, so the global
|
||||
// batch is processed on one device. Returns (loss trace, final params on host).
|
||||
fn run_single_gpu(cfg: Config, corpus: &Corpus, dcfg: &DdpConfig) -> (Vec<f32>, Vec<Vec<f32>>) {
|
||||
@@ -386,3 +426,128 @@ fn ddp_throughput_scaling() {
|
||||
);
|
||||
}
|
||||
}
|
||||
|
||||
/// T21 regression: prove dropout is actually LIVE under DDP, and that p=0 is
|
||||
/// bit-identical to the no-dropout path. Guards the V9-PILOT launcher-wiring gap —
|
||||
/// `train_ddp` had no `--dropout` flag and `train_rank` never called `model.train()`,
|
||||
/// so under DDP every forward ran in the default eval mode and dropout was a silent
|
||||
/// identity regardless of config. Op/single-GPU tests never exercised dropout-under-
|
||||
/// DDP, so it slipped through; this test runs the real launcher path (`train_rank`).
|
||||
///
|
||||
/// With dropout fixed across the 4 sub-runs, all three checks below would FAIL on the
|
||||
/// pre-T21 code: (a) the p>0 trace would be bit-identical to p=0 (model stuck in eval
|
||||
/// mode → identity), and (c) `is_training()` would be false after the run.
|
||||
#[test]
|
||||
fn ddp_dropout_is_live_and_p0_bit_identical() {
|
||||
let world = 2usize;
|
||||
if device::device_count().unwrap_or(0) < world as i32 {
|
||||
eprintln!("skip: need >= {world} GPUs");
|
||||
return;
|
||||
}
|
||||
|
||||
let vocab = 64usize;
|
||||
let corpus = synth_corpus(vocab, 4096);
|
||||
let steps = 20usize;
|
||||
// eval_every < steps so a periodic eval fires MID-run (flipping the model to
|
||||
// eval mode via eval_loss → model.eval()). The per-step model.train() must
|
||||
// restore training mode so dropout stays live across the eval boundary — this is
|
||||
// exactly the train/eval discipline the pilot called out. A held-out slice gives
|
||||
// rank 0 something to eval on.
|
||||
let valid = synth_corpus(vocab, 512);
|
||||
let base_dcfg = DdpConfig {
|
||||
seq_len: 32,
|
||||
batch_size: 8, // global; 4 per rank with world=2
|
||||
accum_steps: 1,
|
||||
steps,
|
||||
schedule: LrSchedule {
|
||||
max_lr: 3e-3,
|
||||
min_lr: 3e-4,
|
||||
warmup: 3,
|
||||
total: steps,
|
||||
},
|
||||
weight_decay: 0.1,
|
||||
max_grad_norm: 1.0,
|
||||
log_every: 1_000_000, // silence per-step logging
|
||||
seed: 7,
|
||||
eval_every: 7, // fires at steps 6, 13, 19 — flips to eval mode mid-run
|
||||
eval_batches: 4,
|
||||
ckpt_path: None,
|
||||
};
|
||||
|
||||
// (1) p=0 config — the no-dropout baseline. cfg.dropout defaults to 0.0.
|
||||
let cfg_p0 = test_config(vocab);
|
||||
assert_eq!(cfg_p0.dropout, 0.0, "baseline cfg must have dropout 0");
|
||||
let (loss_p0, params_p0, _) = run_ddp2(cfg_p0, &corpus, Some(&valid), &base_dcfg);
|
||||
|
||||
// (2) Same config, dropout disabled by p=0 but explicitly set — must be the
|
||||
// SAME run (sanity: setting dropout=0 doesn't perturb anything).
|
||||
let mut cfg_p0b = test_config(vocab);
|
||||
cfg_p0b.dropout = 0.0;
|
||||
let (loss_p0b, params_p0b, _) = run_ddp2(cfg_p0b, &corpus, Some(&valid), &base_dcfg);
|
||||
|
||||
// (3) Same config + data + seed, but dropout p=0.2 ON.
|
||||
let mut cfg_p = test_config(vocab);
|
||||
cfg_p.dropout = 0.2;
|
||||
let (loss_p, _params_p, train_flag_p) = run_ddp2(cfg_p, &corpus, Some(&valid), &base_dcfg);
|
||||
|
||||
// GATE A — p=0 is bit-identical to the no-dropout path (regression guard).
|
||||
// ops::dropout(p=0) is a clone no-op regardless of training mode, so these two
|
||||
// runs must agree to the last bit on BOTH the loss trace and the final params.
|
||||
let mut max_loss_diff = 0.0f32;
|
||||
for (a, b) in loss_p0.iter().zip(&loss_p0b) {
|
||||
max_loss_diff = max_loss_diff.max((a - b).abs());
|
||||
}
|
||||
let mut max_param_diff = 0.0f32;
|
||||
for (a, b) in params_p0.iter().zip(¶ms_p0b) {
|
||||
for (x, y) in a.iter().zip(b) {
|
||||
max_param_diff = max_param_diff.max((x - y).abs());
|
||||
}
|
||||
}
|
||||
println!(
|
||||
"T21 GATE A (p=0 bit-identical): max |loss diff| = {max_loss_diff:.3e}, \
|
||||
max |param diff| = {max_param_diff:.3e}"
|
||||
);
|
||||
assert_eq!(
|
||||
max_loss_diff, 0.0,
|
||||
"p=0 DDP loss trace not bit-identical to no-dropout path"
|
||||
);
|
||||
assert_eq!(
|
||||
max_param_diff, 0.0,
|
||||
"p=0 DDP final params not bit-identical to no-dropout path"
|
||||
);
|
||||
|
||||
// GATE B — dropout is LIVE with p>0 under DDP. If model.train() were not wired
|
||||
// (the pre-T21 bug), the model would stay in eval mode and the p=0.2 forward
|
||||
// would be IDENTITY → loss trace bit-identical to p=0. A real, sizeable
|
||||
// difference proves dropout masks are actually applied during the training
|
||||
// forward (and survive the mid-run eval flips, since model.train() is re-asserted
|
||||
// each step). Inverted scaling + masking perturbs every step, so the gap is large.
|
||||
let mut max_live_diff = 0.0f32;
|
||||
for (a, b) in loss_p0.iter().zip(&loss_p) {
|
||||
max_live_diff = max_live_diff.max((a - b).abs());
|
||||
}
|
||||
println!(
|
||||
"T21 GATE B (dropout live): p0[last]={:.6} p0.2[last]={:.6} max |loss diff| = {max_live_diff:.3e}",
|
||||
loss_p0.last().unwrap(),
|
||||
loss_p.last().unwrap()
|
||||
);
|
||||
assert!(
|
||||
max_live_diff > 1e-3,
|
||||
"p=0.2 DDP loss trace matches p=0 — dropout is NOT live under DDP \
|
||||
(model.train() not wired): max |loss diff| {max_live_diff:.3e}"
|
||||
);
|
||||
|
||||
// GATE C — train_rank leaves the model in TRAINING mode (direct proof that
|
||||
// model.train() was called and survives the final-step eval). On the pre-T21
|
||||
// code this would be false (model never left the default eval mode).
|
||||
assert!(
|
||||
train_flag_p,
|
||||
"model not in training mode after DDP run — model.train() not wired in train_rank"
|
||||
);
|
||||
|
||||
// No NaN/Inf in the p>0 run (dropout converges normally under DDP).
|
||||
assert!(
|
||||
loss_p.iter().all(|l| l.is_finite()),
|
||||
"p=0.2 DDP loss has non-finite values"
|
||||
);
|
||||
}
|
||||
|
||||
@@ -131,6 +131,11 @@ forward 里保持不变**——本设计天然满足：mask 只由 `(seed, i)`
|
||||
- **DDP（T8）**：每 rank 独立跑自己的 forward/backward，各自的 mask 由各 rank 的 `base_seed` 决定。
|
||||
本任务的 DDP 闸门是「loss 对单卡 / 跨 rank 参数一致」，在 **dropout 关（默认 p=0）** 的回归配置下跑，
|
||||
不引入跨 rank mask 同步需求（p>0 时各 rank mask 本就该不同，属正常 DDP 语义）。
|
||||
- **⚠️ T18 的 launcher wiring gap → FIXED in T21**：T18 只把 dropout 接进**单卡** `train.rs`，
|
||||
`train_ddp` bin/`train_rank` loop **没接**（无 `--dropout` flag、从不调 `model.train()`），
|
||||
所以 DDP 路径下 dropout 被静默忽略——V9-PILOT 全栈实跑才暴露（op + 单卡测试覆盖不到 launcher 级）。
|
||||
**T21** 补齐：`train_ddp` 加 `--dropout`、`train_rank` 每步 `model.train()`（eval 后 restore），
|
||||
并加 DDP-dropout 回归测试（p>0 下 dropout live + p=0 逐位一致）。见 known-issues「DDP-dropout wiring」。
|
||||
- **梯度累积（T16）/ flash（T14）**：本分支独立于二者，不依赖其未合并改动。
|
||||
|
||||
## 验证方法
|
||||
|
||||
@@ -29,6 +29,7 @@
|
||||
| T16 | 算法/Infra | **梯度累积**（N 个 micro-step：每个 micro-loss `×1/N` 再 backward，tape SUM 累加 → 一次 AdamW step+zero；`--accum-steps`）；**DDP 只在累积边界 all-reduce**（中间 micro-step 不发 NCCL，`/world` 与 `1/N` 正交）；显存随 micro 不随有效 batch | 等效大 batch**逐位贴合**（loss rel 8.5e-8、grad rel 3.8e-5）；`accum=1` 逐位回归(0.00)；DDP+accum 对单卡 loss 5.7e-7/跨 rank 一致；**显存平**：同有效 batch 64，big-batch 27.7GB→accum(4×16) **7.2GB(−74%)**（big-batch OOM 而 accum 装下）；全回归+xserv 闭环 md5 一致 |
|
||||
| T18 | 算法 | **dropout**（手写 counter-based 设备 RNG → Bernoulli mask，训练 inverted 1/(1-p) scaling、eval 恒等）；新 autodiff `dropout` 算子（fwd 生成+施加 mask，bwd 用同 mask），接 residual/ffn 两处；`--dropout` flag 默认 0 | 固定 seed grad-check 过；E[out]≈input + keep≈1-p；**p=0 与无 dropout 逐位一致**；recompute(T13) 组合下梯度仍逐位一致（counter-based seed 重算复现同 mask）；全回归 + xserv 闭环绿（导出/推理 dropout 关） |
|
||||
| T17 | Infra | **process-per-GPU**（torchrun 式：`launch_processes` 每卡 spawn 一个 worker 进程=独立 CUDA context；launcher 一次性铸 `ncclUniqueId` 后 **hex 编码注入子进程 env**——无共享 FS/TCP、无竞态；worker 读 env→bind device→`DdpContext::init`+`build_model`+`train_rank` **全复用 T8 零改动**；新 `train_ddp_mp` bin/`ddp_proc` test，**保留 thread-per-GPU 旧路径**）；scope=process-per-GPU only（ZeRO-1 用户 drop）（Phase 2） | 正确性全绿：proc vs 单卡 loss 5.67e-7、**proc vs thread-per-GPU 1.5e-7**、跨 rank 1.19e-7(<1e-6)、全回归+xserv 闭环 md5 逐位一致 `b04fc9f9`。**⚠️关键发现（实测证伪原假设）：本尺度 process-per-GPU 对吞吐中性**——thread vs proc @ {1,2,4,8} = {1.00/1.61/2.98/**5.27**}× vs {1.00/1.60/2.94/**5.31**}×（差<1% 噪声内）；8 卡全 95–99% util ⇒ 残留 ~5.3×@8 非线性是 **NCCL all-reduce + 本机 PCIe 拓扑墙**，**非**单 CUDA context 串行（KI-5/T11 doc 的猜想被钉死推翻，方法论同 T11 证伪「分桶 all-reduce」）。净价值=落地 torchrun 式标准链路 + 把误导性 backlog 项实测关闭；默认训练路径不变 |
|
||||
| T21 | Infra | **DDP-dropout wiring fix**（V9-PILOT 暴露：T18 只把 dropout 接进单卡 `train.rs`，`train_ddp` bin 无 `--dropout` flag、`train_rank` 从不调 `model.train()` → DDP 下 dropout 被静默忽略。补：`--dropout` flag + `train_rank` 每步 `model.train()`，镜像单卡 train/eval 纪律——`eval_loss` 翻 eval 后由每步 `train()` restore）；加 DDP-dropout 回归测试堵缺口 | DDP-dropout 回归测试绿：p>0 下 dropout **live**（loss 轨迹对 p=0 有可观差异，pre-T21 会逐位相同）、p=0 对无 dropout 路径**逐位一致**、run 后 `is_training()==true`；既有 DDP loss-match/跨 rank 测试不变。**元教训：op/单卡单元测试漏掉 launcher 级 integration gap，只有真实启动器端到端跑（pilot）才暴露** |
|
||||
|
||||
---
|
||||
|
||||
|
||||
@@ -13,6 +13,15 @@ _(KI-1 fixed in T10. KI-5 fixed in T11. KI-2 fixed in T12. **KI-3（激活重计
|
||||
|
||||
## Fixed
|
||||
|
||||
### DDP-dropout wiring（launcher 漏接 dropout）— `FIXED` (T21)
|
||||
- **背景（V9-PILOT 暴露）**：T18 dropout 在**单卡** `train.rs` 完整接好（`--dropout` flag → `cfg.dropout`，每步 `model.train()`，eval 用 `model.eval()`），op 级 + 单卡都测过。但 V9-PILOT 全栈端到端跑（DDP 8 卡 + dropout0.1 + flash + GQA + accum + bf16）时发现 **DDP 路径根本没接 dropout**：`train_ddp` bin **无 `--dropout` flag、从不设 `cfg.dropout`**，且 `ddp.rs::train_rank` **从不调 `model.train()`** → 模型停在默认 eval 模式，`ops::dropout` 恒等 → DDP 下 dropout **被静默忽略，无论 config 怎么设**。模型 + autodiff 完全支持 dropout（T18），漏的纯是 **DDP launcher / 训练 loop 的 wiring**。
|
||||
- **为何 op/单卡测试没抓到**：dropout 的测试只覆盖**单卡训练循环 + op 级 grad-check**，从没在 **DDP 路径下**跑过 dropout。`train_rank` 是独立于单卡 `train()` 的另一条 loop，二者共享 model/autodiff 但**各自布线 train/eval 纪律** —— 单卡那条对了不代表 DDP 那条对。**元教训：op 级 + 单 GPU 单元测试能漏掉 launcher 级 integration gap**；只有把特性放进**真实启动器路径**端到端跑（pilot 做的事）才暴露。修复随手补了 DDP 路径的回归测试堵这个缺口。
|
||||
- **修复（[docs/17-dropout.md](17-dropout.md)）**：① `train_ddp.rs` 加 `--dropout <p>` flag（默认 0 = 关，对齐旧行为）并设 `cfg.dropout`；② `ddp.rs::train_rank` 每步 micro-batch 循环前调 `model.train()`，镜像单卡 loop 的 train/eval 纪律——**关键**：`eval_loss()` 内部 `model.eval()` 翻成 eval 模式且**不还原**，所以每步重新 assert `model.train()`，dropout 才能跨 eval 边界保持活跃。
|
||||
- **正确性（新增 DDP-dropout 回归测试 `ddp_dropout_is_live_and_p0_bit_identical`，跑真实 `train_rank` 启动器路径）**：① **GATE A**——`p=0` 下 DDP loss 轨迹 + 末态参数对无 dropout 路径**逐位一致**（`ops::dropout(p=0)` 是 clone no-op，回归保护）；② **GATE B**——`p=0.2` 的 loss 轨迹对 `p=0` **有可观差异**（>1e-3），证 dropout mask 真在训练 forward 应用（pre-T21 代码停在 eval 模式 → 二者会逐位相同，此 gate 会 FAIL）；③ **GATE C**——run 后 `model.is_training()==true`（直接证 `model.train()` 被调用且跨末步 eval 存活）；④ p>0 run 无 NaN/Inf。测试故意启用 `eval_every < steps` 让 eval 中途翻 eval 模式，验证每步 `model.train()` 的 restore 纪律。默认 `--dropout 0` 下既有 DDP loss-match + 跨 rank 测试**不变**（回归保护）。
|
||||
- **commit**：见 T21 提交链（`distributed: --dropout flag + model.train() per step in train_rank` / `test: DDP-dropout regression (live under DDP + p=0 bit-identical)` / 文档更新）。
|
||||
|
||||
---
|
||||
|
||||
### process-per-GPU（torchrun 式独立 CUDA context）— `CLOSED / 实测负结果` (T17)
|
||||
- **背景**：KI-5（T11）修掉 per-op `cudaMalloc` 串行后，8 卡 scaling 从 ~1.3× 恢复到 **~5×@8**，但残留 ~5×@8 非完美线性。T11 doc / KI-5「残留」推测下一步是 **process-per-GPU**（每 rank 独立进程 + 独立 CUDA context，torchrun 式）——理由是「N rank 线程共享单 CUDA primary context，kernel-launch/cuBLAS 仍在 context 级串行」。**T17 把这条 torchrun 式链路落地并实测，证伪了该推测。**
|
||||
- **实现（[docs/16-process-per-gpu.md](16-process-per-gpu.md)）**：`xtrain-distributed` 加 `proc.rs`——`launch_processes` 每卡 spawn 一个 worker 进程（re-exec current_exe + `XTRAIN_{RANK,WORLD,LOCAL_RANK,NCCL_ID}` env）；**launcher 一次性铸 `ncclUniqueId` 后 hex 编码注入子进程 env**（无共享 FS/TCP、无轮询、无竞态——id 在子进程出生前就原子就绪）；worker 读 env → bind device（独立 CUDA context）→ `DdpContext::init` + `build_model` + `train_rank` **全部复用 T8 零改动**。新 `train_ddp_mp` bin + `ddp_proc` test；**保留 thread-per-GPU 旧路径**（回归 baseline）。scope=process-per-GPU only（ZeRO-1 用户 drop）。
|
||||
|
||||
Reference in New Issue
Block a user