Masked bf16 attention rounds its scores to bf16 on Jetson Thor (sm_110), but not on A100

Aperta
#4,938 0 commenti 0 reazioni 0 assegnatari Vedi su GitHub

I maintainer di solito rispondono entro 6 giorni

Nessuno ha ancora preso questa issue.

Valutazione

Difficoltà
5/5
Tempo stimato
Più di una settimana
Idoneità per principianti
8/100
Tipo di issue
Bug
Chiarezza
Specificata chiaramente
Stato di attività
Attiva
Stack tecnologico
cpp, python

Direzione di ricerca

The repro is a single Python script that compiles one scaled_dot_product_attention with Torch-TensorRT and prints channel 0 for no mask, a bool mask and a float mask. Run it on a Jetson AGX Thor and on an A100 to confirm the masked outputs differ. Done means the masked Thor output matches the float32-score result (+0.4219) and the random-input error falls back to about the PyTorch level, which needs a fix inside TensorRT's attention kernels.

Scritto dal modello di indicizzazione a partire dal testo della issue.

Descrizione

Module:Accuracy Module:Embedded

What is wrong

On Jetson AGX Thor, a bf16 attention layer with a mask (bool or additive float) computes its softmax scores in
bf16. Without a mask it keeps them in float32. On A100 (sm_80), with the same
TensorRT, the masked layer keeps float32 scores, like PyTorch.

When 2 scores are close, bf16 rounding makes them equal, so the softmax weights change. On random inputs the error
grows about 13 times.

What this blocks

On Jetson Thor, evo1 misses its accuracy check and fails (pytorch/executorch#24353).
lingbot_vla_v2 passes there only because LeRobot keeps its attention out of TensorRT on Thor. That splits it into hundreds of pieces and makes it slower than eager PyTorch.
A fix lets both use fused attention on Thor, as they do on the other GPUs.

Repro

The script compiles one scaled_dot_product_attention with Torch-TensorRT, which builds one IAttention layer.
A query and 2 keys are chosen so that their scaled scores (200.45 and 199.55) round to the same bf16 value. With
float32 scores, output channel 0 is +0.42. With bf16 scores it is 0.

import torch, torch.nn.functional as F, torch_tensorrt, tensorrt

B, H, L, S, D = 8, 8, 50, 805, 64
dev = "cuda"

class Attention(torch.nn.Module):
    def forward(self, q, k, v, mask=None):
        return F.scaled_dot_product_attention(q, k, v, attn_mask=mask)

def near_tie():
    q = torch.zeros(B, H, L, D, device=dev); q[..., 0], q[..., 1] = 16.0, 2.0
    k = torch.zeros(B, H, S, D, device=dev)
    k[..., 0, 0], k[..., 0, 1] = 100.0, 1.796875
    k[..., 1, 0], k[..., 1, 1] = 100.0, -1.796875
    v = torch.zeros(B, H, S, D, device=dev); v[..., 0, 0], v[..., 1, 0] = 1.0, -1.0
    return q.bfloat16(), k.bfloat16(), v.bfloat16()

def random_qkv():
    g = torch.Generator(device=dev).manual_seed(0)
    return tuple((torch.randn(B, H, n, D, device=dev, generator=g) * s).bfloat16()
                 for n, s in ((L, 2.0), (S, 3.0), (S, 1.0)))

def reference(q, k, v, mask):
    s = q.double() @ k.double().transpose(-2, -1) / D**0.5
    if mask is not None:
        s = s.masked_fill(~mask, float("-inf")) if mask.dtype == torch.bool else s + mask.double()
    return s.softmax(-1) @ v.double()

keep = torch.ones(B, 1, 1, S, dtype=torch.bool, device=dev)
keep[1::2, ..., S - S // 8:] = False  # key padding; keys 0 and 1 stay visible
additive = torch.zeros(B, 1, 1, S, device=dev).masked_fill(~keep, float("-inf")).bfloat16().expand(B, H, 1, S).contiguous()

print(torch.cuda.get_device_name(), torch.cuda.get_device_capability(), "TensorRT", tensorrt.__version__)
model = Attention().eval()
for name, mask in (("none", None), ("bool", keep), ("float", additive)):
    args = near_tie() + (() if mask is None else (mask,))
    trt = torch_tensorrt.dynamo.compile(torch.export.export(model, args), arg_inputs=list(args), min_block_size=1)
    with torch.no_grad():
        tie = trt(*args)[..., 0].float().mean().item()
        rargs = random_qkv() + (() if mask is None else (mask,))
        ref = reference(*rargs[:3], mask)
        ok = torch.isfinite(ref)
        err_trt = (trt(*rargs).double() - ref)[ok].abs().max().item()
        err_pt = (model(*rargs).double() - ref)[ok].abs().max().item()
    print(f"mask={name:5} channel 0: {tie:+.4f} (float32 scores give +0.4219); "
          f"random max error vs float64: TensorRT {err_trt:.4f}, PyTorch {err_pt:.4f}")

Results

no mask bool mask float mask random error, masked
Thor (11,0) +0.4219 +0.0000 +0.0000 0.1206 (PyTorch 0.0090)
A100 (8,0) +0.4219 +0.4219 +0.4219 0.0106 (PyTorch 0.0106)

Versions: torch 2.15.0 (CUDA 13.2), torch_tensorrt 2.15.0, TensorRT 11.4.0.106 (all from pip install "torch_tensorrt[executorch]"). Thor: JetPack 7.2.1, driver 595.78, CUDA 13.2.
A100: driver 580.126.09.

Actual

Jetson AGX Thor, driver 595.78:

NVIDIA Thor (11, 0) TensorRT 11.4.0.106
mask=none  channel 0: +0.4219 (float32 scores give +0.4219); random max error vs float64: TensorRT 0.0090, PyTorch 0.0084
mask=bool  channel 0: +0.0000 (float32 scores give +0.4219); random max error vs float64: TensorRT 0.1206, PyTorch 0.0090
mask=float channel 0: +0.0000 (float32 scores give +0.4219); random max error vs float64: TensorRT 0.1206, PyTorch 0.0090

A100 80 GB, driver 580.126.09:

NVIDIA PG509-210 (8, 0) TensorRT 11.4.0.106
mask=none  channel 0: +0.4219 (float32 scores give +0.4219); random max error vs float64: TensorRT 0.0106, PyTorch 0.0106
mask=bool  channel 0: +0.4219 (float32 scores give +0.4219); random max error vs float64: TensorRT 0.0106, PyTorch 0.0106
mask=float channel 0: +0.4219 (float32 scores give +0.4219); random max error vs float64: TensorRT 0.0106, PyTorch 0.0106

Expected

Float32 scores for masked attention on Thor, as on A100.

Lingua principale
C++
Stelle
13.5k
Fork
2.4k
Merge medio
6g 21h
PR unite (30g)
3

Preparare l'ambiente

Come iniziare

  1. Leggi tutta la issue e poi la guida ai contributi del progetto.
  2. Commenta sulla issue per dire che te ne occupi tu — evita che due persone facciano lo stesso lavoro.
  3. Fai un fork del repository e lavora su un branch.
  4. Apri una pull request che faccia riferimento al numero della issue.

Altre issue di NVIDIA/TensorRT

Tutte le issue di NVIDIA/TensorRT

Issue simili

Altre issue su C++

Ricevi le nuove issue nella tua casella

Un breve riepilogo di issue GitHub adatte ai principianti.