[1/4][Refactor] Refactor torchair worker (#1885)

There is a lot torchair specified logic in common code. It results hard
code maintenance. We will create a new torchair module to launch
torchair related logic there. I plan to add 4 PR.

1. Refactor worker (this PR)
- create torchair module and move torchair related code in worker to the
new module
3. Refactor utils
4. Refactor model_runner
5. Refactor attention


- vLLM version: v0.9.2
- vLLM main:
8188196a1c

Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
This commit is contained in:
wangxiyuan
2025-07-21 11:50:46 +08:00
committed by GitHub
parent c32eea96b7
commit af56ae3ed1
5 changed files with 91 additions and 39 deletions

View File

@@ -163,7 +163,10 @@ class NPUPlatform(Platform):
update_aclgraph_sizes(vllm_config)
if parallel_config and parallel_config.worker_cls == "auto":
parallel_config.worker_cls = "vllm_ascend.worker.worker_v1.NPUWorker"
if ascend_config.torchair_graph_config.enabled:
parallel_config.worker_cls = "vllm_ascend.torchair.torchair_worker.NPUTorchairWorker"
else:
parallel_config.worker_cls = "vllm_ascend.worker.worker_v1.NPUWorker"
if cache_config:
if cache_config.block_size is None: