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

[main2main] upgrade vllm main 0202 (#6560)

Browse Source 
### What this PR does / why we need it?
1. Fix `TypeError: FusedMoEParallelConfig.__init__() missing 1 required
positional argument: 'is_sequence_parallel'` due to
https://github.com/vllm-project/vllm/pull/32567
2. Fix ` TypeError: '>' not supported between instances of 'MagicMock'
and 'int'` due to https://github.com/vllm-project/vllm/pull/33035
3. Fix `TypeError: Can't instantiate abstract class AscendMLAImpl with
abstract methods forward_mha, forward_mqa` and AttributeError: 'bool'
object has no attribute 'process_weights_after_loading' due to
https://github.com/vllm-project/vllm/pull/33284
4. Fix `'AscendSharedFusedMoE' object has no attribute
'_routed_input_transform'`due to
https://github.com/vllm-project/vllm/pull/32790
5. Fix `NPUModelRunner._dummy_run() got an unexpected keyword argument
'num_active_loras'` due to
https://github.com/vllm-project/vllm/pull/32005
6. Fix the problem caused by` 'tuple' object has no attribute 'job_id'`
due to https://github.com/vllm-project/vllm/pull/27492
7. Fix the problem that all_moe_layers is not equal to vllm.moe_forward,
vllm.moe_forward_shared due to
https://github.com/vllm-project/vllm/pull/33184
8. Add patch to fix the problem "got multiple values for keyword
argument 'add_special_tokens'" due to
https://github.com/vllm-project/vllm/pull/32863
### Does this PR introduce _any_ user-facing change?

### How was this patch tested?

- vLLM version: v0.15.0
- vLLM main: https://github.com/vllm-project/vllm/commit/v0.15.0

---------

Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
Signed-off-by: Meihan-chen <jcccx.cmh@gmail.com>
Signed-off-by: hfadzxy <starmoon_zhang@163.com>
Co-authored-by: wangxiyuan <wangxiyuan1007@gmail.com>
Co-authored-by: hfadzxy <starmoon_zhang@163.com>
This commit is contained in:
meihanc
2026-02-05 19:31:17 +08:00
committed by GitHub
parent 2c1608265b
commit 922e5c163b
28 changed files with 246 additions and 30 deletions
Download Patch File Download Diff File Expand all files Collapse all files

22
vllm_ascend/attention/mla_v1.py
View File

@@ -1450,6 +1450,28 @@ class AscendMLAImpl(MLAAttentionImpl):
def get_num_actual_tokens(self, attn_metadata: M):
return attn_metadata.num_actual_tokens
def forward_mha(
self,
layer_name: str,
hidden_states: torch.Tensor,
kv_cache: tuple[torch.Tensor],
attn_metadata: M,
need_gather_q_kv: bool = False,
output: torch.Tensor | None = None,
) -> torch.Tensor:
raise NotImplementedError("forward_mha is not supported for MLA attention. Use forward() instead.")
def forward_mqa(
self,
layer_name: str,
hidden_states: torch.Tensor,
kv_cache: tuple[torch.Tensor],
attn_metadata: M,
need_gather_q_kv: bool = False,
output: torch.Tensor | None = None,
) -> torch.Tensor:
raise NotImplementedError("forward_mqa is not supported for MLA attention. Use forward() instead.")
def forward(
self,
layer_name,

21
vllm_ascend/attention/sfa_v1.py
View File

@@ -1062,3 +1062,24 @@ class AscendSFAImpl(MLAAttentionImpl):
torch.distributed.all_to_all_single(attn_output, send, group=get_tp_group().device_group)
return attn_output, True
def forward_mha(
self,
q: torch.Tensor,
kv_c_normed: torch.Tensor,
k_pe: torch.Tensor,
kv_c_and_k_pe_cache: torch.Tensor,
attn_metadata: M,
k_scale: torch.Tensor,
output: torch.Tensor,
) -> None:
raise NotImplementedError("forward_mha is not supported for SFA attention. Use forward() instead.")
def forward_mqa(
self,
q: torch.Tensor | tuple[torch.Tensor, torch.Tensor],
kv_c_and_k_pe_cache: torch.Tensor,
attn_metadata: M,
layer,
) -> tuple[torch.Tensor, torch.Tensor | None]:
raise NotImplementedError("forward_mqa is not supported for SFA attention. Use forward() instead.")