EngineX/xc-llm-ascend
3
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

Main2main upgrade vllm commit to 03 19 17:00 (#7478)

Browse Source 
### What this PR does / why we need it?
Upgrade vllm commit to 2026.03.19.

1.Fix socket removed from StatelessProcessGroup. Upstream vLLM PR
[#36330](https://github.com/vllm-project/vllm/pull/36330) ("elastic_ep:
Fix stateless group port races") refactored StatelessProcessGroup and
removed the socket: socket.socket | None field. The socket ownership was
moved to a new create_tcp_store() helper instead of being stored as a
field on the dataclass.

2.fix `virtual_engine` parameter removed from `set_forward_context().
Upstream [V0 Deprecation] Deprecate virtual engine
[#37195](https://github.com/vllm-project/vllm/pull/37195)

### Does this PR introduce _any_ user-facing change?
NA

### How was this patch tested?
NA

- vLLM version: v0.17.0
- vLLM main:
8b6325758c

---------

Signed-off-by: leo-pony <nengjunma@outlook.com>
This commit is contained in:
Nengjun Ma
2026-03-23 16:25:57 +08:00
committed by GitHub
parent caa71e50ca
commit 8e2c59e1ee
12 changed files with 28 additions and 20 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
vllm_ascend/patch/worker/patch_qwen3_next.py
View File

@@ -32,7 +32,7 @@ from vllm.v1.attention.backends.utils import PAD_SLOT_ID
from vllm_ascend.attention.utils import maybe_save_kv_layer_to_connector
from vllm_ascend.ops.triton.fla.fused_qkvzba_split_reshape import fused_qkvzba_split_reshape_cat
from vllm_ascend.ops.triton.fused_gdn_gating import fused_gdn_gating_patch
from vllm_ascend.utils import enable_sp
from vllm_ascend.utils import enable_sp, vllm_version_is
class AscendQwen3Next_GatedDeltaNet(Qwen3NextGatedDeltaNet):
@@ -124,7 +124,7 @@ class AscendQwen3Next_GatedDeltaNet(Qwen3NextGatedDeltaNet):
non_spec_token_indx = attn_metadata.non_spec_token_indx
spec_state_indices_tensor = attn_metadata.spec_state_indices_tensor # noqa: E501
non_spec_state_indices_tensor = attn_metadata.non_spec_state_indices_tensor # noqa: E501
self_kv_cache = self.kv_cache[forward_context.virtual_engine]
self_kv_cache = self.kv_cache[forward_context.virtual_engine if vllm_version_is("0.18.0") else 0]
conv_state = self_kv_cache[0].transpose(-1, -2)
ssm_state = self_kv_cache[1]
num_actual_tokens = attn_metadata.num_actual_tokens