From 36b5c27993cd9438d45a86d48fa201f9aa6a6513 Mon Sep 17 00:00:00 2001 From: fzyzcjy <5236035+fzyzcjy@users.noreply.github.com> Date: Tue, 25 Mar 2025 09:12:36 +0800 Subject: [PATCH] Update buffer.py --- deep_ep/buffer.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/deep_ep/buffer.py b/deep_ep/buffer.py index 11a2ce3..14948be 100644 --- a/deep_ep/buffer.py +++ b/deep_ep/buffer.py @@ -479,7 +479,7 @@ class Buffer: Moreover, not all tokens are valid, only some of the `num_max_dispatch_tokens_per_rank * num_ranks` are, as we do not synchronize CPU received count with GPU (also not incompatible with CUDA graph if synced). recv_count: a tensor shaped `[num_local_experts]` with type `torch.int`, indicating how many tokens each - expert receive. As mentioned before, all not tokens are valid in `recv_x`. + expert receive. As mentioned before, not all tokens are valid in `recv_x`. handle: the communication handle to be used in the `low_latency_combine` function. event: the event after executing the kernel (valid only if `async_finish` is set). hook: the receiving hook function (valid only if `return_recv_hook` is set).