### What this PR does / why we need it?
This PR fixes a bug in Xlite
backend(https://atomgit.com/openeuler/GVirt/issues/1), The direct cause
of the problem is that the XModel::PrepareAttn function obtained an
illegal number of tokens to be inferred, -540. This illegal value is due
to the padding feature of inference in graph mode and the residual state
across steps. This issue is triggered when a prefill request is newly
added in a step and a decode ends simultaneously. It is first fixed
using num_decode_tokens instead of attn_metadata.num_decodes.
1. In graph mode, vllm_ascend has padding characteristics. In the
_prepare_inputs function, if the number of tokens to be inferred is less
than the set threshold (8 in this case), the attn_metadata.num_decode
array will be expanded to 8.
2. Meanwhile, vllm_ascend uses the class variable self.query_start_loc
of NPUModelRunner to record the tokens to be inferred. Due to poor
coordination with the graph mode padding mechanism when crossing steps,
in some cases (such as when a decode request is completed in a certain
step and a new prefill request is added at the same time), negative
values may be calculated for attn_metadata.query_lens.
3. After type conversion, the negative values in query_lens cause an
overflow. Xlite detects that the number of tokens to be inferred for the
decode request is too large and triggers a "decode len too long" alert.
### Does this PR introduce _any_ user-facing change?
No
### How was this patch tested?
Same with https://atomgit.com/openeuler/GVirt/issues/1
- vLLM version: v0.13.0
- vLLM main:
https://github.com/vllm-project/vllm/commit/2f4e6548efec402b913ffddc8726230d9311948d
Signed-off-by: wwwumr <1127858301@qq.com>
### What this PR does / why we need it?
Close the **Full Graph** mode to temporarily avoid accuracy issue for
**Qwen3-Next-80B-A3B-Instruct-W8A8**.
### Does this PR introduce _any_ user-facing change?
N/A
### How was this patch tested?
- vLLM version: v0.13.0
- vLLM main:
https://github.com/vllm-project/vllm/commit/2f4e6548efec402b913ffddc8726230d9311948d
---------
Signed-off-by: InSec <1790766300@qq.com>
### What this PR does / why we need it?
The rotary algorithm in deepseek indexer should be neox-style instead of
gptj style. PR #4413 fix this accuracy bug with new triton kernel. This
PR fixes original pytorch version.
### Does this PR introduce _any_ user-facing change?
None
### How was this patch tested?
CI passed with existing test.
- vLLM version: 86e178f7c4d8c3b0eaf3c8e3f810a83f63b90e24
- vLLM main:
https://github.com/vllm-project/vllm/commit/86e178f7c4d8c3b0eaf3c8e3f810a83f63b90e24
Signed-off-by: whx-sjtu <2952154980@qq.com>
### What this PR does / why we need it?
1. add PaddleOCR-VL.md in the `docs/source/tutorials/`
2. add PaddleOCR-VL index in `docs/source/tutorials/index.md`
### Does this PR introduce _any_ user-facing change?
No
### How was this patch tested?
by CI
- vLLM version: v0.13.0
- vLLM main:
https://github.com/vllm-project/vllm/commit/7157596103666ee7ccb7008acee8bff8a8ff1731
Signed-off-by: zouyizhou <zouyizhou@huawei.com>
### What this PR does / why we need it?
This addresses the issue brought up by #5356 and #4963, and we believe
the unnecessary conditions are the root cause.
Change the unpad trigger to be driven by actual size mismatches
(num_reqs vs base_num_reqs or scheduled vs input token counts) rather
than specific speculative-method flags. Then remove brittle workarounds
that forced request counts and sliced query start locations.
This prevents incorrect indexing and length mismatches during
speculative decoding and makes metadata unpadding more robust across
scheduling modes.
### Does this PR introduce _any_ user-facing change?
None.
### How was this patch tested?
Tested by existing cases.
- vLLM version: v0.13.0
- vLLM main:
https://github.com/vllm-project/vllm/commit/8be6432bdaf6275664d857b1e5e9bf8ed1ce299e
---------
Signed-off-by: Yizhou Liu <liu_yizhou@outlook.com>
### What this PR does / why we need it?
Adapted sp to eagle3.
There may still be some problems, e.g., accuracy in some scenes,
`sp`+`dp`...
We will fix them later.
### Does this PR introduce _any_ user-facing change?
N/A
### How was this patch tested?
We tested it mainly in a new `e2e`.
```shell
pytest -s tests/e2e/singlecard/spec_decode/test_v1_spec_decode.py::test_llama_qwen_eagle_acceptance
```
```text
.
=============================== 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
============= 3 passed, 1 skipped, 2 warnings in 142.05s (0:02:22) =============
```
It passed.
- vLLM version: v0.13.0
- vLLM main:
https://github.com/vllm-project/vllm/commit/7157596103666ee7ccb7008acee8bff8a8ff1731
Signed-off-by: drslark <slarksblood@qq.com>
### What this PR does / why we need it?
Correcting some outdated use cases:
`tests/e2e/singlecard/test_aclgraph_accuracy.py::test_models_output` ->
`tests/e2e/singlecard/test_aclgraph_accuracy.py::test_piecewise_res_consistency`
### Does this PR introduce _any_ user-facing change?
### How was this patch tested?
- vLLM version: v0.13.0
- vLLM main:
https://github.com/vllm-project/vllm/commit/2f4e6548efec402b913ffddc8726230d9311948d
Signed-off-by: wangli <wangli858794774@gmail.com>
### What this PR does / why we need it?
EPLB currently does not have CI related to aclgraph and redundancy
experts; this PR adds them.
release on #5529
### Does this PR introduce _any_ user-facing change?
### How was this patch tested?
Tested the use cases to be added in this PR.
PASSED
====================================================== 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
====================================================== 1 passed, 2
warnings in 272.24s (0:04:32)
=====================================================
- vLLM version: v0.13.0
- vLLM main:
https://github.com/vllm-project/vllm/commit/8be6432bdaf6275664d857b1e5e9bf8ed1ce299e
Signed-off-by: shenchuxiaofugui <1311027364@qq.com>
### What this PR does / why we need it?
1. MagicMTP (paper: "Block Verification Accelerates Speculative
Decoding") was introduced to consider the influence among multiple draft
tokens, improving the acceptance rate without compromising accuracy.
2. Added Triton and PyTorch implementations, and added E2E test cases.
### Does this PR introduce _any_ user-facing change?
MagicMTP will automatically take effect when the parameter
"num_speculative_tokens" >= 3.
- vLLM version: v0.13.0
- vLLM main:
https://github.com/vllm-project/vllm/commit/7157596103666ee7ccb7008acee8bff8a8ff1731
Signed-off-by: chenaoxuan <cax1165@163.com>
### What this PR does / why we need it?
func `get_kv_cache_spec` in model_runner changed a lot and caused error
in cpuoffloading connector which is copied from model_runner, this PR
adapts to new implemented `get_kv_cache_spec` to fix it.
### How was this patch tested?
- vLLM version: v0.11.0
- vLLM main:
https://github.com/vllm-project/vllm/commit/2918c1b49c88c29783c86f78d2c4221cb9622379
Signed-off-by: lidenghui <lidenghui1110@gmail.com>
### What this PR does / why we need it?
- Delete the environment variable
`VLLM_ASCEND_ENABLE_FLASHCOMM2_OSHARED`
- Introduce layer_sharding as a configurable feature in
additional_config
- Revise the term "shared weight" to "shard weight."
Configuration : The feature is opt-in via the additional_config
argument:
```
--additional-config '{
"layer_sharding": ["o_proj", "q_b_proj"]
}'
```
This is orthogonal to standard tensor parallelism and weight replication
strategies. It is treated as a separate, explicit feature.It can be used
in any scenario, combined with the
flashcomm2https://github.com/vllm-project/vllm-ascend/pull/3232 feature
or the ShardedCP #4702 feature, to achieve significant performance.
- vLLM version: v0.12.0
- vLLM main:
https://github.com/vllm-project/vllm/commit/ad32e3e19ccf0526cb6744a5fed09a138a5fb2f9
---------
Signed-off-by: zzhx1 <zzh_201018@outlook.com>
Signed-off-by: zzhxx <zhangzihang23@mails.ucas.ac.cn>
Signed-off-by: chenxiao <Jaychou1620@Gmail.com>
Co-authored-by: clrs97 <524936896@qq.com>
Co-authored-by: Levi-JQ <yujinqi2@huawei.com>
Co-authored-by: chenxiao <Jaychou1620@Gmail.com>
### What this PR does / why we need it?
1.replace moe_gating_top_k from torch_npu with custom op
2.enable the renorm function of moe_gating_top_k in softmax scenerio
### Does this PR introduce _any_ user-facing change?
No
### How was this patch tested?
No need test
- vLLM version: v0.13.0
- vLLM main:
https://github.com/vllm-project/vllm/commit/7157596103666ee7ccb7008acee8bff8a8ff1731
---------
Signed-off-by: ZCG12345 <2097562023@qq.com>
### What this PR does / why we need it?
1. Accuracy testing no longer compares eager and graph modes; instead,
it directly extracts the golden result under the graph mode
configuration (the implicit purpose of this case is to verify whether
modifications affect existing results)
2. Next step: finer-grained supervision of logits/sampler results
### Does this PR introduce _any_ user-facing change?
### How was this patch tested?
- vLLM version: release/v0.13.0
- vLLM main:
https://github.com/vllm-project/vllm/commit/254f6b986720c92ddf97fbb1a6a6465da8e87e29
Signed-off-by: wangli <wangli858794774@gmail.com>
## What this PR does / why we need it?
This PR fixes the `AttentionMaskBuilder` singleton initialization issue
introduced in PR #4779 and removes the unused `pcp_prefill_mask` field.
### Background
After PR #4779 made `AttentionMaskBuilder` a singleton with `@singleton`
decorator, the class constructor now requires a `device` parameter.
However, two initialization sites were still using the old parameterless
constructor, causing failures.
### Changes
1. **Fix singleton initialization**
- Fixed `AttentionMaskBuilder()` → `AttentionMaskBuilder(self.device)`
in `AscendMLAMetadataBuilder.__init__()`
- Fixed `AttentionMaskBuilder()` → `AttentionMaskBuilder(self.device)`
in `AscendAttentionMetadataBuilder.__init__()`
2. **Remove unused field**
- Removed `pcp_prefill_mask` field from
`AscendPrefillContextParallelMetadata` (never used in codebase)
- Updated related test assertions
### Related
- Issue #5463
- PR #4779 (Unify all mask generation methods)
- PR #5389 (Make AttentionMaskBuilder singleton)
## Does this PR introduce _any_ user-facing change?
No. This is an internal refactoring.
## How was this patch tested?
- ✅ Local testing: No linter errors
- ✅ Unit tests for attention modules verified
- ⏳ CI pipeline
Signed-off-by: lico67373 <918688502@qq.com>
Co-authored-by: weijinqian0 <1184188277@qq.com>
### What this PR does / why we need it?
When launching the service in the scenario where the
cudagraph_mode is set to FULL and Eagle3 acceleration is enabled for
inference, an error in fia will cause graph capture to fail. This PR
fixes the issue.
### Does this PR introduce _any_ user-facing change?
### How was this patch tested?
- vLLM version: v0.13.0
- vLLM main:
https://github.com/vllm-project/vllm/commit/7157596103666ee7ccb7008acee8bff8a8ff1731
Signed-off-by: WithHades <244036962@qq.com>
### What this PR does / why we need it?
Resolving the issue of insufficient resources during service operation
when PCP is enabled in a piecewise scenario.
When enabling PCP and executing in piecewise mode, the curl request
fails due to insufficient resources, resulting in the error message "The
resources are insufficient." Through profiling analysis, it was found
that the PCP communication domain also occupies streams and consumes
resources. Therefore, when updating aclgraph sizes, the PCP
communication domain needs to be taken into account.
### Does this PR introduce _any_ user-facing change?
### How was this patch tested?
- vLLM version: release/v0.13.0
- vLLM main:
https://github.com/vllm-project/vllm/commit/bc0a5a0c089844b17cb93f3294348f411e523586
---------
Signed-off-by: weiguihua2 <weiguihua2@huawei.com>
### What this PR does / why we need it?
To adapt different shapes of the KV cache, UCM optimized the
initialization of store by moving it into `register_kv_caches`.
Therefore, this update adds `register_kv_caches` interface to
UCMConnectorV1.
### How was this patch tested?
- vLLM version: v0.13.0
- vLLM main:
https://github.com/vllm-project/vllm/commit/2f4e6548efec402b913ffddc8726230d9311948d
Signed-off-by: UnifiedCacheManager <unifiedcachem@163.com>
# What this PR does / why we need it?
Add DeepSeek-V3.2-W8A8 dual-node nightly CI test and update A3 nightly
test configuration:
1. Add DeepSeek-V3.2-W8A8 dual-node test:
tests/e2e/nightly/multi_node/config/DeepSeek-V3_2-W8A8-A3-dual-nodes.yaml
- 2 nodes, 16 NPUs per node (32 NPUs total)
- Configuration: 2P+1D (data-parallel-size=4, tensor-parallel-size=8,
data-parallel-size-local=2)
- Includes performance and accuracy benchmarks with GSM8K dataset
2. Update A3 nightly workflow: .github/workflows/nightly_test_a3.yaml
- Added DeepSeek-V3.2-W8A8 dual-node test to the A3 nightly test matrix
- Test name: multi-node-dpsk3.2-2node
3. Improve test scripts: Updated
.github/workflows/_e2e_nightly_multi_node.yaml and related scripts for
better multi-node testing support
test on A3 instances
- Performance baseline: 1 (threshold: 0.97)
- Accuracy baseline: 95% (threshold: 5%)
- Test dataset: GSM8K with 512 prompts for performance, gsm8k-lite for
accuracy
---------
Signed-off-by: guozr <guozr1997@hotmail.com>
Co-authored-by: guozr <guozr1997@hotmail.com>
### What this PR does / why we need it?
Purpose: initialize padded slot mapping buffer to prevent garbage
values.
In PCP mode, the `pcp_padded_slot_mapping` buffer is reused across
invocations. Without explicit initialization, this buffer retain stale
values from previous runs, which can lead to incorrect results.
This change ensures the buffer is filled with -1.
### Does this PR introduce _any_ user-facing change?
No.
### How was this patch tested?
- vLLM version: v0.13.0
- vLLM main:
https://github.com/vllm-project/vllm/commit/2f4e6548efec402b913ffddc8726230d9311948d
---------
Signed-off-by: F.Liu <liufeng248@huawei.com>
Co-authored-by: F.Liu <liufeng248@huawei.com>
### What this PR does / why we need it?
1. add `COMPILATION_PASS_KEY` constant
2. clean up useless platform interface `empty_cache`, `synchronize`,
`mem_get_info`, `clear_npu_memory`
3. rename `CUSTOM_OP_REGISTERED` to `_CUSTOM_OP_REGISTERED`
4. remove uesless env `VLLM_ENABLE_CUDAGRAPH_GC`
NPUPlatform is the interface called by vLLM. Do not call it inner
vllm-ascend.
### Does this PR introduce _any_ user-facing change?
This PR is just a cleanup. All CI should pass.
### How was this patch tested?
- vLLM version: v0.13.0
- vLLM main:
https://github.com/vllm-project/vllm/commit/7157596103666ee7ccb7008acee8bff8a8ff1731
Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
### What this PR does / why we need it?
This PR builds upon PR
https://github.com/vllm-project/vllm-ascend/pull/5011 and aims to
further enhance the npu_graph_ex_passes module. Based on prior work, we
have added graph optimization support for the add_rms_quant fused
operator in scenarios where a bias term is present—ensuring the fusion
pattern is correctly registered and matched into the computation graph.
For validation, we switched to the Qwen3-235B-A22B-W8A8 model for
SPPatternWithBias and Qwen3-32B model for SPPattern. Benchmark results
show that, compared to the unfused baseline, enabling this fusion pass
significantly improves inference throughput for W8A8 quantized models.
For more details can refer to the
RFC:https://github.com/vllm-project/vllm-ascend/issues/4715
### Does this PR introduce _any_ user-facing change?
no
### How was this patch tested?
```
llm = LLM(
model=model,
tensor_parallel_size=GPUs_per_dp_rank,
enforce_eager=False,
enable_expert_parallel=enable_expert_parallel,
trust_remote_code=trust_remote_code,
gpu_memory_utilization=0.98,
max_num_batched_tokens=512,
# load_format="dummy",
max_model_len=2048,
max_num_seqs=16,
quantization="ascend",
additional_config={
"refresh": True,
"enable_npugraph_ex": True
},
compilation_config={
"cudagraph_capture_sizes": [8, 16],
"cudagraph_mode": "FULL_DECODE_ONLY",
},
)
if profile_dir:
llm.start_profile()
outputs = llm.generate(prompts, sampling_params)
if profile_dir:
llm.stop_profile()
for i, output in enumerate(outputs):
if i >= 5:
break
prompt = output.prompt
generated_text = output.outputs[0].text
print(
f"DP rank {global_dp_rank}, Prompt: {prompt!r}, "
f"Generated text: {generated_text!r}"
)
```
- vLLM version: v0.13.0
- vLLM main:
https://github.com/vllm-project/vllm/commit/7157596103666ee7ccb7008acee8bff8a8ff1731
Signed-off-by: cjian <2318164299@qq.com>
### What this PR does / why we need it?
[Bugfix] fix dcp_only bug and add e2e accuracy test for dcp only and pcp
only
this pr fix the bug of accuracy test when decode_parallel_size>1 and
prefill_context_parallel_size=1.
### Does this PR introduce _any_ user-facing change?
NO
### How was this patch tested?
- vLLM version: v0.13.0
- vLLM main:
https://github.com/vllm-project/vllm/commit/7157596103666ee7ccb7008acee8bff8a8ff1731
---------
Signed-off-by: zhenwenqi2024 <zhenwenqi_2022@qq.com>
### What this PR does / why we need it?
Revert PR 5253 to fix the smoking problem
### Does this PR introduce _any_ user-facing change?
Does not.
### How was this patch tested?
It was tested in the failure case.
Signed-off-by: Rifa <865071616@qq.com>