EngineX/xc-llm-ascend
3
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity
2,783 Commits 2 Branches 0 Tags
v0.18.0
Commit Graph

4 Commits

Author SHA1 Message Date
SILONG ZENG
bd571cf6d6 [Main2Main] Upgrade vLLM to 0303 (#6944) 
### What this PR does / why we need it?
break:
- https://github.com/vllm-project/vllm/pull/34102 
Disable_full param replaced with valid_modes/invalid_modes API
- https://github.com/vllm-project/vllm/pull/35503
Now must return float compilation_time
- https://github.com/vllm-project/vllm/pull/35564
New sequence_lengths param added
- https://github.com/vllm-project/vllm/pull/33807
A check was performed (if runner_backend != "auto")
- https://github.com/vllm-project/vllm/pull/34861
`BaseDeviceCommunicator` now accesses PyTorch's internal `pg_map` to
check process group state
- https://github.com/vllm-project/vllm/pull/35274

**Important change:**
- https://github.com/vllm-project/vllm/pull/28672

`matcher_utils` directly accesses `torch.ops._C.*` during the import
phase. In the Ascend environment, some unregistered ops trigger
`AttributeError`, causing e2e initialization failure.

https://github.com/vllm-project/vllm-ascend/actions/runs/22607260487/job/65502047131#step:10:2323

https://github.com/vllm-project/vllm/blob/main/vllm/compilation/passes/fusion/matcher_utils.py#L29

This PR adds temporary compatibility placeholders (rms_norm,
fused_add_rms_norm, rotate_embedding, static/dynamic fp8 quant,
silu_and_mul) to
`vllm_ascend/patch/platform/patch_fusion_matcher_compat_ops.py` to
ensure no crashes during the import phase. Upstream repairs will be
considered later.

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

### How was this patch tested?

- vLLM version: v0.16.0
- vLLM main:
15d76f74e2

---------

Signed-off-by: MrZ20 <2609716663@qq.com>
Signed-off-by: gcanlin <canlinguosdu@gmail.com>
Co-authored-by: Meihan-chen <jcccx.cmh@gmail.com>
Co-authored-by: Claude Code <noreply@anthropic.com>
Co-authored-by: gcanlin <canlinguosdu@gmail.com>
 2026-03-06 09:08:52 +08:00
lty
295018ec0f [Refactor]Refactor of vllm_ascend/distributed module (#5719) 
### What this PR does / why we need it?
Based on the RFC:https://github.com/vllm-project/vllm-ascend/issues/5604

This PR is a refactoring of vllm_ascend/distributed, moving all
kv_transfer realtaed codes into a dedicated folder, which has already
been done in vLLM

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

### How was this patch tested?


- vLLM version: v0.13.0
- vLLM main:
2f4e6548ef

---------

Signed-off-by: lty <linhebiwen@gmail.com>
 2026-01-15 08:57:40 +08:00
yiz-liu
a6bb502e70 [2/N][Feat] Add MC2 communication method for MoE layers (#2469) 
### What this PR does / why we need it?
This method replaces the previous all-gather approach for small numbers
of tokens.

The key changes include:
- A new `AscendFusedMoE` layer that handles token splitting, local
computation, and final aggregation via all-gather.
- Logic in the model runner to dynamically select between the new MC2
method and the existing all-gather method based on the number of input
tokens.
- Sharding the MoE communication mask across tensor-parallel ranks.

### Does this PR introduce _any_ user-facing change?
None.

### How was this patch tested?
Test case fixed.


- vLLM version: v0.10.1.1
- vLLM main:
b00e69f8ca

---------

Signed-off-by: Yizhou Liu <liu_yizhou@outlook.com>
 2025-08-26 19:05:23 +08:00
yangqinghao-cmss
ee6f79c44a Add ut for test_communicator.py (#2293) 
### What this PR does / why we need it?

Add ut for test_communicator.py 

- vLLM version: v0.10.0
- vLLM main:
e5ebeeba53

Signed-off-by: yangqinghao-cmss <yangqinghao_yewu@cmss.chinamobile.com>
 2025-08-09 08:26:04 +08:00