[Fix] Restore deferred layer dumps and pin SentencePiece for InternVL (#41777)
This commit is contained in:
@@ -74,7 +74,7 @@ dependencies = [
|
||||
"regex",
|
||||
"requests",
|
||||
"scipy",
|
||||
"sentencepiece",
|
||||
"sentencepiece==0.2.1", # 0.2.2 rejects null pieces in InternVL tokenizers.
|
||||
"setproctitle",
|
||||
"sgl-deep-ep==0.1.2",
|
||||
"sgl-deep-gemm==0.2.0",
|
||||
|
||||
@@ -54,7 +54,7 @@ dependencies = [
|
||||
"regex",
|
||||
"requests",
|
||||
"scipy",
|
||||
"sentencepiece",
|
||||
"sentencepiece==0.2.1", # 0.2.2 rejects null pieces in InternVL tokenizers.
|
||||
"setproctitle",
|
||||
"smg-grpc-servicer>=0.9.0",
|
||||
"soundfile==0.13.1",
|
||||
|
||||
@@ -55,7 +55,7 @@ dependencies = [
|
||||
"regex",
|
||||
"requests",
|
||||
"scipy",
|
||||
"sentencepiece",
|
||||
"sentencepiece==0.2.1", # 0.2.2 rejects null pieces in InternVL tokenizers.
|
||||
"setproctitle",
|
||||
"smg-grpc-servicer>=0.9.0",
|
||||
"soundfile==0.13.1",
|
||||
|
||||
@@ -56,7 +56,7 @@ runtime_base = [
|
||||
"regex",
|
||||
"requests",
|
||||
"scipy",
|
||||
"sentencepiece",
|
||||
"sentencepiece==0.2.1", # 0.2.2 rejects null pieces in InternVL tokenizers.
|
||||
"setproctitle",
|
||||
"smg-grpc-servicer>=0.9.0",
|
||||
"soundfile==0.13.1",
|
||||
|
||||
@@ -54,7 +54,7 @@ dependencies = [
|
||||
"regex",
|
||||
"requests",
|
||||
"scipy",
|
||||
"sentencepiece",
|
||||
"sentencepiece==0.2.1", # 0.2.2 rejects null pieces in InternVL tokenizers.
|
||||
"setproctitle",
|
||||
"sglang-kernel-xpu @ https://github.com/sgl-project/whl/releases/download/v0.3.0+xpu/sglang_kernel_xpu-0.3.0-cp310-abi3-manylinux_2_38_x86_64.whl",
|
||||
"smg-grpc-servicer>=0.9.0",
|
||||
|
||||
@@ -1780,6 +1780,18 @@ class _SGLangPlugin(_FrameworkPlugin):
|
||||
if isinstance(value, self.PPProxyTensors):
|
||||
return {k: v for k, v in value.tensors.items()}
|
||||
|
||||
from sglang.srt.layers.layer_boundary.output import UnreducedOutput
|
||||
from sglang.srt.layers.layer_boundary.residual.stream import OwedOutput
|
||||
|
||||
# Observe rank-local storage without completing the deferred reduction or
|
||||
# consuming the residual stream. Opaque handoffs and consumed handles have
|
||||
# no tensor to dump.
|
||||
if isinstance(value, UnreducedOutput):
|
||||
return {"": value.partial}
|
||||
if isinstance(value, OwedOutput):
|
||||
tensor = value.contribution.value
|
||||
return {"": tensor} if tensor is not None else {}
|
||||
|
||||
return None
|
||||
|
||||
def detect_layer_id(self, module: "torch.nn.Module") -> Optional[int]:
|
||||
|
||||
Reference in New Issue
Block a user