[refactor] refactor deepseek-related files (#2849)
### What this PR does / why we need it?
This PR deletes ~2K lines of code about deepseek modeling. It falls back
CustomDeepseekV2 modules to original vllm implementations and adapts
some modifications in vllm about deepseek and moe.
### Does this PR introduce _any_ user-facing change?
No.
### How was this patch tested?
E2E vllm serving with torchair graph mode and eager mode.
- vLLM version: v0.10.2
- vLLM main:
759ef49b15
---------
Signed-off-by: linfeng-yuan <1102311262@qq.com>
Signed-off-by: Yizhou Liu <liu_yizhou@outlook.com>
Co-authored-by: yiz-liu <136800916+yiz-liu@users.noreply.github.com>
Co-authored-by: Yizhou Liu <liu_yizhou@outlook.com>
This commit is contained in:
@@ -17,4 +17,3 @@
|
||||
|
||||
import vllm_ascend.patch.platform.patch_common.patch_distributed # noqa
|
||||
import vllm_ascend.patch.platform.patch_common.patch_mamba_config # noqa
|
||||
import vllm_ascend.patch.platform.patch_common.patch_shared_fused_moe # noqa
|
||||
|
||||
@@ -18,3 +18,4 @@
|
||||
import vllm_ascend.patch.worker.patch_common.patch_distributed # noqa
|
||||
import vllm_ascend.patch.worker.patch_common.patch_logits # noqa
|
||||
import vllm_ascend.patch.worker.patch_common.patch_minicpm # noqa
|
||||
import vllm_ascend.patch.worker.patch_common.patch_shared_fused_moe # noqa
|
||||
|
||||
Reference in New Issue
Block a user