[Dependency] Upgrade FlashInfer to 0.7.2 and restore KDA auto backend (#61913)
Signed-off-by: Anerudhan Gopal <agopal@nvidia.com> Co-authored-by: OpenAI Codex <noreply@openai.com>
This commit is contained in:
co-authored by
OpenAI Codex
parent
19b0efce30
commit
af28c171f5
@@ -10,7 +10,7 @@ torchaudio==2.11.0
|
|||||||
torchvision==0.29.0 # Required for phi3v processor. See https://github.com/pytorch/vision?tab=readme-ov-file#installation for corresponding version
|
torchvision==0.29.0 # Required for phi3v processor. See https://github.com/pytorch/vision?tab=readme-ov-file#installation for corresponding version
|
||||||
torchcodec >= 0.14
|
torchcodec >= 0.14
|
||||||
PyNvVideoCodec==2.0.4
|
PyNvVideoCodec==2.0.4
|
||||||
flashinfer-python==0.7.1
|
flashinfer-python==0.7.2
|
||||||
apache-tvm-ffi==0.1.11
|
apache-tvm-ffi==0.1.11
|
||||||
tilelang==0.1.12
|
tilelang==0.1.12
|
||||||
nvidia-cudnn-frontend>=1.19.1
|
nvidia-cudnn-frontend>=1.19.1
|
||||||
|
|||||||
@@ -456,7 +456,7 @@ def _flashinfer_kda_prefill(
|
|||||||
beta_is_logit=True,
|
beta_is_logit=True,
|
||||||
seq_order=seq_order,
|
seq_order=seq_order,
|
||||||
prefill_workspace=prefill_workspace,
|
prefill_workspace=prefill_workspace,
|
||||||
backend="cute-dsl",
|
backend="auto",
|
||||||
)
|
)
|
||||||
return output, initial_state
|
return output, initial_state
|
||||||
|
|
||||||
|
|||||||
Reference in New Issue
Block a user