EngineX/xc-llm-ascend
3
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity
1,816 Commits 3 Branches 0 Tags
30778f371b6e95492e927f9149b7ee6ff317258b
Commit Graph

11 Commits

Author SHA1 Message Date
wjunLu
fca2f948c1 [E2E Refactor] Enable skipped e2e case (#5287) 
### What this PR does / why we need it?

The test case `tests/e2e/multicard/test_data_parallel.py` was skipped
due to the errors encountered during migration from Ascend A2 to A3, the
details are as follows
```
(EngineCore_DP0 pid=17833) RuntimeError: npu_moe_distribute_dispatch_v2:build/CMakeFiles/torch_npu.dir/compiler_depend.ts:161 NPU function error: call aclnnMoeDistributeDispatchV3 failed, error code is 561002
(EngineCore_DP0 pid=17833) [ERROR] 2025-12-23-07:36:19 (PID:17833, Device:0, RankID:-1) ERR00100 PTA call acl api failed.
(EngineCore_DP0 pid=17833) EZ9999: Inner Error!
(EngineCore_DP0 pid=17833) EZ9999[PID: 17833] 2025-12-23-07:36:19.237.396 (EZ9999):  HCCL_BUFFSIZE is too SMALL, maxBs = 512, h = 2048, epWorldSize = 2, localMoeExpertNum = 64, sharedExpertNum = 0, tokenNeedSizeDispatch = 4608, tokenNeedSizeCombine = 4096, k = 8, NEEDED_HCCL_BUFFSIZE(((maxBs * tokenNeedSizeDispatch * ep_worldsize * localMoeExpertNum) + (maxBs * tokenNeedSizeCombine * (k + sharedExpertNum))) * 2) = 609MB, HCCL_BUFFSIZE=200MB.[FUNC:MoeDistributeDispatchA3TilingFuncImpl][FILE:moe_distribute_dispatch_v2_tiling.cc][LINE:941]
(EngineCore_DP0 pid=17833)         TraceBack (most recent call last):
(EngineCore_DP0 pid=17833)        MoeDistributeDispatchV2 do tiling failed, ret is -1.
(EngineCore_DP0 pid=17833)        Check NnopbaseExecutorDoTiling(executor) failed
(EngineCore_DP0 pid=17833)        Check NnopbaseExecutorTilingAndUpdateBinInfo(executor) failed
(EngineCore_DP0 pid=17833)        Check NnopbaseExecutorMatchCache(executor) failed
(EngineCore_DP0 pid=17833)        Check NnopbaseRunForWorkspace(*executor, workspaceSize) failed
```

### Does this PR introduce _any_ user-facing change?
None
### How was this patch tested?
After fixed, I ran `pytest -sv --durations=0
tests/e2e/multicard/test_data_parallel.py`, and the result looks good
```
========================================================================================= warnings summary =========================================================================================
<frozen importlib._bootstrap>:241
  <frozen importlib._bootstrap>:241: DeprecationWarning: builtin type SwigPyPacked has no __module__ attribute

<frozen importlib._bootstrap>:241
  <frozen importlib._bootstrap>:241: DeprecationWarning: builtin type SwigPyObject has no __module__ attribute

-- Docs: https://docs.pytest.org/en/stable/how-to/capture-warnings.html
======================================================================================== slowest durations =========================================================================================
112.69s call     tests/e2e/multicard/test_data_parallel.py::test_qwen_inference_dp2[32-vllm-ascend/Qwen3-30B-A3B-W8A8]
88.11s call     tests/e2e/multicard/test_data_parallel.py::test_qwen_inference_dp2[32-Qwen/Qwen3-30B-A3B]
70.06s call     tests/e2e/multicard/test_data_parallel.py::test_qwen_inference_dp2[32-Qwen/Qwen3-0.6B]

(6 durations < 0.005s hidden.  Use -vv to show these durations.)
============================================================================ 3 passed, 2 warnings in 270.88s (0:04:30) ============================================================================
```
- vLLM version: release/v0.13.0
- vLLM main:
ad32e3e19c

Signed-off-by: wjunLu <wjunlu217@gmail.com>
 2025-12-25 09:18:05 +08:00
SILONG ZENG
29a93daa82 [CI]refactor: standardize test case naming convention (#5243) 
### What this PR does / why we need it?
- Standardize test case naming in `vllm-ascend/tests/e2e/multicard/` to
follow the `<model>_<feature>_<distributed>` convention.

- vLLM version: release/v0.13.0
- vLLM main:
ad32e3e19c

---------

Signed-off-by: MrZ20 <2609716663@qq.com>
Signed-off-by: root <root@LAPTOP-VQKDDVMG.localdomain>
Co-authored-by: root <root@LAPTOP-VQKDDVMG.localdomain>
 2025-12-23 14:13:42 +08:00
SILONG ZENG
e56dba9b0d [CI]cleanup e2e test (#4800) 
### What this PR does / why we need it?
This PR refactors the E2E multicard test suite to improve test case
identification and maintainability. Specifically, it renames various
test functions to be more descriptive (explicitly indicating model
families like Qwen/DeepSeek and parallelism strategies like DP/TP/PP/EP)
and cleans up outdated or redundant test configurations in the offline
distributed inference tests.

**Key Changes:**
1. Test Function Renaming (Standardization): Renamed multiple test
functions across **`tests/e2e/multicard/`** to include clear
suffixes/prefixes regarding the model and parallel strategy. This helps
differentiate test cases in CI logs and prevents naming collisions.

**`test_aclgraph_capture_replay.py`:** 
- `test_aclgraph_capture_replay_dp2` ->
`test_aclgraph_capture_replay_metrics_dp2`

**`test_data_parallel.py`:**
- `test_data_parallel_inference` -> `test_qwen_inference_dp2`

**`test_data_parallel_tp2.py`:**
- `test_data_parallel_inference` -> `test_qwen_inference_dp2_tp2`

**`test_expert_parallel.py`:**
- `test_e2e_ep_correctness` -> `test_deepseek_correctness_ep`

**`test_external_launcher.py`:**
- `test_external_launcher` -> `test_qwen_external_launcher`
- `test_moe_external_launcher` -> `test_qwen_moe_external_launcher_ep`
- `test_external_launcher_and_sleepmode` ->
`test_qwen_external_launcher_with_sleepmode`
- `test_external_launcher_and_sleepmode_level2` ->
`test_qwen_external_launcher_with_sleepmode_level2`
- `test_mm_allreduce` ->
`test_qwen_external_launcher_with_matmul_allreduce`

**`test_full_graph_mode.py`:** 
- `test_models_distributed_Qwen3_MOE_TP2_WITH_FULL_DECODE_ONLY` ->
`test_qwen_moe_with_full_decode_only`
- `test_models_distributed_Qwen3_MOE_TP2_WITH_FULL` ->
`test_qwen_moe_with_full`

**`test_fused_moe_allgather_ep.py`:** 
- `test_generate_with_allgather `->
`test_deepseek_moe_fused_allgather_ep`
- `test_generate_with_alltoall` -> `test_deepseek_moe_fused_alltoall_ep`

**`test_offline_weight_load.py`:**
- `test_offline_weight_load_and_sleepmode` ->
`test_qwen_offline_weight_load_and_sleepmode`

**`test_pipeline_parallel.py`:**
- `test_models` -> `test_models_pp2`

2. Distributed Inference Cleanup
(**`test_offline_inference_distributed.py`**):

**model list changes:**
```
QWEN_DENSE_MODELS = [
-     "vllm-ascend/Qwen3-8B-W8A8", "vllm-ascend/Qwen2.5-0.5B-Instruct-W8A8"
+     "vllm-ascend/Qwen3-8B-W8A8",
]
```

```
- QWEN_W4A8_OLD_VERSION_MODELS = [
-    "vllm-ascend/Qwen3-8B-W4A8",
- ]

- QWEN_W4A8_NEW_VERSION_MODELS = [
-     "vllm-ascend/DeepSeek-V3-W4A8-Pruing",
-     "vllm-ascend/DeepSeek-V3.1-W4A8-puring",
- ]

+ DEEPSEEK_W4A8_MODELS = [
+      "vllm-ascend/DeepSeek-V3.1-W4A8-puring",
+ ]
```

**Test Function Changes:**
- removed `test_models_distributed_QwQ`
- removed `test_models_distributed_Qwen3_W8A8`
- removed `test_models_distributed_Qwen3_W4A8DYNAMIC_old_version`
- `test_models_distributed_Qwen3_W4A8DYNAMIC_new_version` ->
`test_models_distributed_Qwen3_W4A8DYNAMIC`

- vLLM version: v0.12.0
- vLLM main:
ad32e3e19c

---------

Signed-off-by: MrZ20 <2609716663@qq.com>
 2025-12-11 20:35:32 +08:00
Yizhou
134e011896 [Test] Temporarily skips Qwen3-30B-A3B-W8A8 data parallel test case (#4857) 
### What this PR does / why we need it?
This case is breaking CI, please see
https://github.com/vllm-project/vllm-ascend/actions/runs/20084930558/job/57620266368?pr=4854

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

### How was this patch tested?
None.

Signed-off-by: Yizhou Liu <liu_yizhou@outlook.com>
 2025-12-10 11:05:32 +08:00
Wang Kunpeng
a9c4b8604a [main][bugfix] bugfix for qwen3 moe quantization (#4599) 
### What this PR does / why we need it?
Fix the issue where the qwen3 moe service cannot be started due to
upgrading the vllm version

Error info:
AttributeError: 'AscendFusedMoE' object has no attribute 'use dp
chunking'

### Does this PR introduce _any_ user-facing change?
no


- vLLM version: v0.11.2

---------

Signed-off-by: Wang Kunpeng <1289706727@qq.com>
 2025-12-01 23:48:57 +08:00
wangxiyuan
0d14f635b4 upgrade torch npu version (#4433) 
vLLM graph feature now rely on torch >=2.8. To make graph mode work, we
need upgrade torch version as well. For long term support, upgrade torch
to a newer one is good to go as well.

Related vLLM change: https://github.com/vllm-project/vllm/pull/25110


- vLLM version: v0.11.2
- vLLM main: https://github.com/vllm-project/vllm/commit/v0.11.2
 2025-12-01 19:01:55 +08:00
lilinsiman
1b424fb7f1 ACLgraph enable: Test cases revisions for all features (#3388) 
### What this PR does / why we need it?
This PR revise the test cases of various features on the warehouse which
add the enablement of aclgraph to the test cases.

### Does this PR introduce _any_ user-facing change?
no

### How was this patch tested?
ut

- vLLM version: v0.11.0rc3
- vLLM main: https://github.com/vllm-project/vllm/commit/v0.11.0

Signed-off-by: lilinsiman <lilinsiman@gmail.com>
 2025-10-17 17:15:19 +08:00
wangxiyuan
fef18b60bc Refactor e2e CI (#2276) 
Refactor E2E CI to make it clear and faster
1. remove some uesless e2e test
2. remove some uesless function
3. Make sure all test runs with VLLMRunner to avoid oom error
4. Make sure all ops test end with torch.empty_cache to avoid oom error
5. run the test one by one to avoid resource limit error


- vLLM version: v0.10.1.1
- vLLM main:
a344a5aa0a

Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
 2025-09-02 09:02:22 +08:00
Mengqing Cao
af04ee9e7a [MoE][Dist] Fix Qwen MoE accuracy bug in DP scenario (#1856) 
### What this PR does / why we need it?
Fix Qwen MoE accuracy bug in DP scenario.

Now the implentment of `FusedMoE` in vLLM use `All2AllManager` to
manager different all2all algorithm branch. And the default branch use
`Multicast` in `dispatch` phase and `all_reduce` in `combine` phase,
which are not implented in vLLM-Ascend. This leading to invoking into a
default implentment in `base_communicator`, with empty `dispatch` and
`combine` operations, thus causing the accuracy issue on it.

This pr is a temporary workaround, refacting all2all in vLLM-Ascend
could be a better way.


- vLLM version: v0.10.0
- vLLM main:
ad57f23f6a

---------

Signed-off-by: MengqingCao <cmq0113@163.com>
 2025-08-04 10:24:18 +08:00
leo-pony
2ee90461d0 Fix e2e data parallel test: add resource release code (#1881) 
### What this PR does / why we need it?
Fix e2e data parallel test: add resource release code and give more time
to engine to pause their processing loops before exiting.

### Does this PR introduce _any_ user-facing change?
No

- vLLM version: v0.9.2
- vLLM main:
5895afd780

Signed-off-by: leo-pony <nengjunma@outlook.com>
 2025-07-19 11:39:48 +08:00
Mengqing Cao
52317f92cb [DP] Tiny fix of dp and update example (#1273) 
### What this PR does / why we need it?
Add `max_num_tokens_across_dp` to AscendMetadata to fix dp

This pr fixes the bug introduced by
https://github.com/vllm-project/vllm-ascend/pull/1229, which add an arg
`max_num_tokens_across_dp` when dp_size > 1.

Signed-off-by: MengqingCao <cmq0113@163.com>
 2025-06-25 11:03:04 +08:00