[CI]Moe alltoall communication optimization (#1067)

[CI]Moe alltoall communication optimization
The DeepSeek V3/R1 model has 256 routing experts. During parallel
inference, if the load of an EP rank is high, the overall communication
and computing time is slowed down, which becomes a weakness of parallel
inference because the load is unevenly distributed. However, the data
volume in the prefill phase is large, and the inter-card communication
time consumption/calculation time consumption and the data volume are
closely related to each other. Therefore, less non-linear precision loss
can be used to obtain a near-linear performance improvement.

During parallel inference, global synchronization occurs during
communication. As a result, the card with low load completes the
calculation first and waits for the card with the highest load to
complete the calculation. Therefore, if the load is unbalanced, the card
with high load slows down the overall time consumption. Significant
performance gains can be achieved by discarding a small number of
tokens, which is unacceptable in some precision-sensitive scenarios.
However, similar to quantification, it is a solution that uses an
acceptable precision loss in some scenarios for performance. In
addition, a trade-off between performance and precision can be achieved
by configuring a proportion of discarded tokens.

Perform the test on A3. The batch size is 8 (B), the prompt length is
3.5K tokens (S), and the parallel configuration is as follows: AttnDP=2,
AttnTP=8, MoeTP=1, and MoeEP=16. In this sence, we got a 10%-15%
performance gain.

Plus, the next version, we'll have an alltoallv moe.

---------

Signed-off-by: weijinqian_v1 <weijinqian@huawei.com>
Co-authored-by: weijinqian_v1 <weijinqian@huawei.com>

vllm_ascend/envs.py

@@ -112,6 +112,11 @@ env_variables: Dict[str, Callable[[], Any]] = {
     "VLLM_ASCEND_MODEL_EXECUTE_TIME_OBSERVE":
     lambda: bool(int(os.getenv("VLLM_ASCEND_MODEL_EXECUTE_TIME_OBSERVE", '0'))
                  ),
+    # MOE_ALL2ALL_BUFFER:
+    #   0: default, normal init.
+    #   1: enable moe_all2all_buffer.
+    "MOE_ALL2ALL_BUFFER":
+    lambda: bool(int(os.getenv("MOE_ALL2ALL_BUFFER", '0'))),
     # VLLM_ASCEND_ACL_OP_INIT_MODE:
     #   0: default, normal init.
     #   1: delay init until launch aclops.