### What this PR does / why we need it?
bugfix short squence has no respone. This pull request refactors the
event handling for KV cache reshaping in mla_v1.py by centralizing the
reshape_cache_event creation and recording within the _mla_preprocess
function, ensuring it covers both decode and prefill operations.
Signed-off-by: wangxiaoteng <wangxiaoteng@huawei.com>
### What this PR does / why we need it?
Introduce a check to not using asynchronous communication under
`enable_dsa_cp_with_layer_shard` branch on capturing mode. This change
prevents potential stream and event issues when operating in
graph/capturing mode, ensuring safer communication practices.
### Does this PR introduce _any_ user-facing change?
No.
### How was this patch tested?
E2E test with dsv32 + FC1 + FULL_DECODE_ONLY +
kv_transfer_config(kv_both)
---------
Signed-off-by: chenchuw886 <chenchuw@huawei.com>
Co-authored-by: chenchuw886 <chenchuw@huawei.com>
### What this PR does / why we need it?
1. This PR cherry pick commit that contains current best performance at
3.5k/1.5k and 128k/1k from main to 0.18.0 branch.
2. This PR introduce MiniMax-M2.7 0day information to users.
3. To finish previous step we also changes MiniMax doc name from
MiniMax-M2.5.md to MiniMax-M2.md
---------
Signed-off-by: limuyuan <limuyuan3@huawei.com>
Co-authored-by: limuyuan <limuyuan3@huawei.com>
### What this PR does / why we need it?
This PR adds description of preemption into FAQs in vLLM-Ascend. This
FAQ stats:
- how preemption affects the performance of a vLLM server.
- how reduce the negative impacts of preemption.
The reason why we add this FAQ is that we find that the origin
description of preemption in vLLM is not very straightforward. If
preemption causes performance drop, users might not be aware that this
is caused by Preemption.
### Does this PR introduce _any_ user-facing change?
No.
Signed-off-by: Angazenn <supperccell@163.com>
### What this PR does / why we need it?
Fix the nightly pip binary install doc test fail.
### Does this PR introduce _any_ user-facing change?
NA
### How was this patch tested?
Nightly doc test
Signed-off-by: leo-pony <nengjunma@outlook.com>
### What this PR does / why we need it?
Cherry-picked from #8062
This PR adds support for the Ascend950 NPU by updating the `npu-smi
info` parsing logic to handle interface changes. It also improves
robustness by ensuring that `SOC_VERSION` actually takes effect by
disabling `get_chip_type` given this environment variable.
### Does this PR introduce _any_ user-facing change?
No.
### How was this patch tested?
CI passed.
Signed-off-by: linfeng-yuan <1102311262@qq.com>
### What this PR does / why we need it?
This PR fixes and simplifies the CI configuration for Qwen3 32B.
The main changes are:
- Remove the redundant `Qwen3-32B-Int8-A3-Feature-Stack3.yaml` config
and consolidate the CI setup into `Qwen3-32B-Int8.yaml`.
- Improve runtime stability by adding
`PYTORCH_NPU_ALLOC_CONF=expandable_segments:True` and setting
`--max-num-seqs 80`.
- Update the accuracy benchmark from `aime2024` to `gsm8k-lite`, and
adjust the related dataset config, output length, baseline, and
threshold accordingly.
These changes make the Qwen3 32B CI easier to maintain and more stable
in nightly validation.
---------
Signed-off-by: ZYang6263 <zy626375@gmail.com>
…and PCP across machines
<!-- Thanks for sending a pull request!
BEFORE SUBMITTING, PLEASE READ
https://docs.vllm.ai/en/latest/contributing/overview.html
-->
### What this PR does / why we need it?
<!--
- Please clarify what changes you are proposing. The purpose of this
section is to outline the changes and how this PR fixes the issue.
If possible, please consider writing useful notes for better and faster
reviews in your PR.
- Please clarify why the changes are needed. For instance, the use case
and bug description.
- Fixes #
-->
### Does this PR introduce _any_ user-facing change?
<!--
Note that it means *any* user-facing change including all aspects such
as API, interface or other behavior changes.
Documentation-only updates are not considered user-facing changes.
-->
### How was this patch tested?
<!--
CI passed with new added/existing test.
If it was tested in a way different from regular unit tests, please
clarify how you tested step by step, ideally copy and paste-able, so
that other reviewers can test and check, and descendants can verify in
the future.
If tests were not added, please describe why they were not added and/or
why it was difficult to add.
-->
Signed-off-by: DreamLeader <2270923832@qq.com>
### What this PR does / why we need it?
This PR is cherry-pick from #8029.
This PR aims to fix attention state of short prompt for correct
forwarding. Since a batch of short prompts (prefill tokens less than or
equal to num_spec_tokens + 1) will be treated as decode requests (by
split_decodes_and_prefills), its original PrefillNoCache attention state
contradicts. Thus these short prompts will be passed into a mismatched
branch and incur errors.
### Does this PR introduce _any_ user-facing change?
N/A
### How was this patch tested?
by ci
Signed-off-by: Zetong Li <slippersss@126.com>
This pull request reverts previous changes to switch to FIA and instead
implements npu_ring_mla for MLA prefill operations(#5704 ). The change
streamlines the attention mechanism by removing unnecessary metadata
tracking and updating the underlying NPU operations to use the
ring-based MLA kernel. This adjustment ensures better compatibility and
performance for MLA prefill tasks within the vLLM Ascend backend.
Highlights
- Migration to npu_ring_mla: Replaced the usage of
npu_fused_infer_attention_score (FIA) with npu_ring_mla for MLA prefill
operations across the codebase to improve performance and alignment with
the intended architecture.
- Cleanup of redundant metadata: Removed
chunk_actual_seq_lengths_kv_list and actual_seq_lengths_q from various
metadata structures as they are no longer required for the updated
attention implementation.
- Test suite updates: Updated unit tests in test_mla_cp.py and
test_mla_v1.py to mock npu_ring_mla instead of the deprecated FIA
functions and adjusted test assertions to reflect the new implementation
details.
Signed-off-by: weijinqian_v1 <weijinqian@huawei.com>
Co-authored-by: weijinqian_v1 <weijinqian@huawei.com>
### What this PR does / why we need it?
Cherry-picked from #8039
Restore the setting of MC2 `global_bs` and `mc2_mask` handling when
`all_reduce` across DP group cannot be skipped. Ascend MC2 ops require
`global_bs=0` + `mc2_mask` while enabling inter-node roce hierarchical
communication. PR #4983 always passed non-zero `global_bs` without
`mc2_mask`, which is incompatible with hierarchy comm raised in PR #7583
**Changes:**
- Add `should_skip_allreduce_across_dp_group()` to `utils.py` with
hierarchy constraint
- Set `global_bs=0` when allreduce is not skipped; pass `mc2_mask`
accordingly
- Add `mc2_mask` field to `MoEMC2CombineMetadata` for dispatch→combine
propagation
### Does this PR introduce _any_ user-facing change?
No. But this PR fixes cross-super-node communication function on A3 with
`enable_mc2_hierarchy_comm=True` in `additional_config` and `export
HCCL_INTRA_ROCE_ENABLE=1`.
### How was this patch tested?
E2E serving succeeded and CI pssed.
- vLLM version: v0.18.0
- vLLM main:
14acf429ac
---------
Signed-off-by: linfeng-yuan <1102311262@qq.com>
### What this PR does / why we need it?
Enabling temperature in post-processing on 310P devices can cause the
service to stall and eventually hang. We first traced the issue to a
timeout where the temperature-related `div` operator was waiting for
results from a sub-stream. After investigating the preceding operators,
we finally identified the root cause as the `q.exponential_()` operator,
which is not well supported on 310P and triggers an internal issue in
the `add` kernel.
### Does this PR introduce _any_ user-facing change?
NA
### How was this patch tested?
This patch was thoroughly tested locally（accuracy-dataset test and
stress test）. It is not easy to design a proper unit test for this case,
and I appreciate your understanding.
Signed-off-by: Tflowers-0129 <2906339855@qq.com>
What this PR does / why we need it?
This pull request performs a comprehensive cleanup of the vLLM Ascend
documentation. It fixes numerous typos, grammatical errors, and phrasing
issues across community guidelines, developer documents, hardware
tutorials, and feature guides. Key improvements include correcting
hardware names (e.g., Atlas 300I), fixing broken links, cleaning up code
examples (removing duplicate flags and trailing commas), and improving
the clarity of technical explanations. These changes are necessary to
ensure the documentation is professional, accurate, and easy for users
to follow.
Does this PR introduce any user-facing change?
No, this PR contains documentation-only updates.
How was this patch tested?
The changes were manually reviewed for accuracy and grammatical
correctness. No functional code changes were introduced.
---------
Signed-off-by: herizhen <1270637059@qq.com>
Signed-off-by: herizhen <59841270+herizhen@users.noreply.github.com>
<!-- Thanks for sending a pull request!
BEFORE SUBMITTING, PLEASE READ
https://docs.vllm.ai/en/latest/contributing/overview.html
-->
### What this PR does / why we need it?
When we launch a PD-disaggregated process and send requests, an
additional processes appear on NPU 0, becasue when a thread has a
primary cuda context, the child thread it creates automatically doesn't
inherit the cuda context. See
https://forums.developer.nvidia.com/t/when-a-thread-has-a-primary-cuda-context-does-the-child-thread-it-creates-automatically-inherit-the-cuda-context/362810.
vLLM has fixed this issue in [pr-37449
](https://github.com/vllm-project/vllm/pull/37449), but version 0.18.0
does not include the fix. Therefore, we need to patch it.
<!--
- Please clarify what changes you are proposing. The purpose of this
section is to outline the changes and how this PR fixes the issue.
If possible, please consider writing useful notes for better and faster
reviews in your PR.
- Please clarify why the changes are needed. For instance, the use case
and bug description.
- Fixes #
-->
### Does this PR introduce _any_ user-facing change?
no
<!--
Note that it means *any* user-facing change including all aspects such
as API, interface or other behavior changes.
Documentation-only updates are not considered user-facing changes.
-->
### How was this patch tested?
<!--
CI passed with new added/existing test.
If it was tested in a way different from regular unit tests, please
clarify how you tested step by step, ideally copy and paste-able, so
that other reviewers can test and check, and descendants can verify in
the future.
If tests were not added, please describe why they were not added and/or
why it was difficult to add.
-->
---------
Signed-off-by: zouyida <zouyida@huawei.com>
Co-authored-by: zouyida <zouyida@huawei.com>
<!-- Thanks for sending a pull request!
BEFORE SUBMITTING, PLEASE READ
https://docs.vllm.ai/en/latest/contributing/overview.html
-->
### What this PR does / why we need it?
<!--
- Please clarify what changes you are proposing. The purpose of this
section is to outline the changes and how this PR fixes the issue.
If possible, please consider writing useful notes for better and faster
reviews in your PR.
- Please clarify why the changes are needed. For instance, the use case
and bug description.
- Fixes #
-->
Cherry-pick from https://github.com/vllm-project/vllm-ascend/pull/7468
- Fix TTFT ratio threshold from 0.8 to 0.4 for prefix cache benchmarks
- Fix max_out_len values for warm_up and benchmark configs
- Applied to both DeepSeek-R1-0528-W8A8 and Qwen3-32B-Int8 configs
### Does this PR introduce _any_ user-facing change?
<!--
Note that it means *any* user-facing change including all aspects such
as API, interface or other behavior changes.
Documentation-only updates are not considered user-facing changes.
-->
### How was this patch tested?
<!--
CI passed with new added/existing test.
If it was tested in a way different from regular unit tests, please
clarify how you tested step by step, ideally copy and paste-able, so
that other reviewers can test and check, and descendants can verify in
the future.
If tests were not added, please describe why they were not added and/or
why it was difficult to add.
-->
Signed-off-by: underfituu <hzhucong@163.com>
backport of #7474
This PR adds C8 (INT8) KV cache quantization support for standard GQA
attention models (e.g., Qwen3-32B W8A8C8). C8 uses static per-channel
quantization scales to store KV cache in INT8, reducing KV cache memory
by ~50% compared to BF16, enabling higher batch concurrency and longer
context lengths on the same hardware.
**Key changes:**
1. **`attention_v1.py`** — New `AscendC8AttentionBackendImpl` subclass
of `AscendAttentionBackendImpl`:
- `_prepare_c8_scales`: Shards per-channel scales/offsets to the current
TP rank and pre-computes BF16 BNSD-shaped antiquant tensors (one-time
per layer).
- `_quantize_kv_to_int8`: Quantizes BF16 K/V to INT8 before
`reshape_and_cache`, using pre-cached inverse scales.
- `_forward_c8_decode`: FIA V1 BNSD paged attention with native INT8 KV
and `perchannel` antiquant mode.
- `_forward_c8_chunked_prefill`: Splits decode (FIA V1 BNSD paged INT8)
and prefill (FIA V1 TND float) into two kernel calls.
- `_forward_c8_fused_infer_attention`: Handles `PrefillNoCache` and
`PrefillCacheHit` states.
2. **`quantization/methods/kv_c8.py`** — New
`AscendC8KVCacheAttentionMethod` scheme:
- Creates `k/v_cache_scale/offset` parameters via
`_c8_kv_scale_weight_loader`, which handles per-channel scale shapes and
lazy resizing.
- Sets `layer.kv_cache_torch_dtype = torch.int8` so
`get_kv_cache_spec()` returns INT8 dtype automatically.
- Upgrades `layer.impl` to `AscendC8AttentionBackendImpl` via class
surgery.
3. **`quantization/modelslim_config.py`** — C8 branch in
`get_quant_method()` activates when `kv_cache_type == "C8"` in
`quant_model_description.json`.
4. **`patch/worker/patch_qwen3_c8.py`** — Intercepts per-channel C8
scale/offset weights before `AutoWeightsLoader` discards them, routing
them to the parameters created by `AscendC8KVCacheAttentionMethod`.
5. **`tests/ut/quantization/test_kv_c8.py`** — Unit tests covering
`_c8_kv_scale_weight_loader`, `AscendC8KVCacheAttentionMethod`, and
`AscendC8AttentionBackendImpl` scale helpers.
Yes. Users can now serve Qwen3-32B W8A8C8 quantized models with INT8 KV
cache on Ascend NPU. The model checkpoint must contain a
`quant_model_description.json` with `"kv_cache_type": "C8"` and
per-channel scale/offset tensors in safetensors.
No changes to the serving CLI — the feature activates automatically when
the quantization config is detected.
Benchmarked with `vllm serve` (TP=8, `max_num_seqs=256`,
`max_model_len=131072`, `enable_chunked_prefill=true`) + `random_bench`
(input_len=10240, output_len=2048, 960 prompts, max_concurrency=192):
```
============ Serving Benchmark Result ============
Successful requests: 960
Failed requests: 0
Maximum request concurrency: 192
Benchmark duration (s): 1359.81
Total input tokens: 9830400
Total generated tokens: 1966080
Request throughput (req/s): 0.71
Output token throughput (tok/s): 1445.85
Peak output token throughput (tok/s): 2304.00
Total token throughput (tok/s): 8675.12
---------------Time to First Token----------------
Mean TTFT (ms): 24598.51
Median TTFT (ms): 23167.02
P50 TTFT (ms): 23167.02
P90 TTFT (ms): 47717.08
P99 TTFT (ms): 84402.61
-----Time per Output Token (excl. 1st token)------
Mean TPOT (ms): 120.76
Median TPOT (ms): 121.50
P50 TPOT (ms): 121.50
P90 TPOT (ms): 127.05
P99 TPOT (ms): 130.13
---------------Inter-token Latency----------------
Mean ITL (ms): 120.70
Median ITL (ms): 90.34
P50 ITL (ms): 90.34
P90 ITL (ms): 93.79
P99 ITL (ms): 101.80
==================================================
```
All attention states verified: `PrefillNoCache`, `PrefillCacheHit`,
`ChunkedPrefill`, `DecodeOnly`.
- vLLM version: v0.17.0
- vLLM main:
8b6325758c
Signed-off-by: lico67373 <918688502@qq.com>
Co-authored-by: LICO67373 <110013619+LICO1314@users.noreply.github.com>
### What this PR does / why we need it?
To avoid misleading users, the unmaintained DSV32 models, such as the
floating-point model, are deleted from the document.This PR removes the
BF16 version entries for DeepSeek-V3.2 from the documentation.
### Does this PR introduce _any_ user-facing change?
No.
### How was this patch tested?
Documentation update only.
Signed-off-by: wyh145 <1987244901@qq.com>
### What this PR does / why we need it?
This PR Qwen3.5-27B ;MiniMax-M2.5-w8a8 ;Qwen3.5-397B-w8a8-mtp acc/perf 3
cases on A3, we need test them daily.
- vLLM version: v0.18.0
- vLLM main:
35141a7eed
Signed-off-by: guxin108 <1252896542@qq.com>
### What this PR does / why we need it?
Fix qwen3Next Nightly CI config in 0.18.0.
backport: #7679
Signed-off-by: Your Name <you@example.com>
Co-authored-by: Your Name <you@example.com>
### What this PR does / why we need it?
Add qwen3vl weights download
### Does this PR introduce _any_ user-facing change?
### How was this patch tested?
Signed-off-by: betta18 <jiangmengyu1@huawei.com>
Co-authored-by: betta18 <jiangmengyu1@huawei.com>
### What this PR does / why we need it?
Add nightly ci test for qwen3vl
### Does this PR introduce _any_ user-facing change?
### How was this patch tested?
Signed-off-by: betta18 <jiangmengyu1@huawei.com>
Co-authored-by: betta18 <jiangmengyu1@huawei.com>
### What this PR does / why we need it?
Enable Flash Comm V1 (sequence parallelism) for Qwen3-VL models (both
dense and MoE variants).
Root cause: Qwen3-VL's deepstack embeddings remain full-size [N, H]
while hidden states become [N/tp_size, H] after reduce-scatter, causing
shape mismatch on add.
### Does this PR introduce _any_ user-facing change?
### How was this patch tested?
- [x] Run Qwen3-VL dense model with FC1 enabled (TP > 1), verify correct
output
- [x] Run Qwen3-VL MoE model with FC1 enabled (TP > 1), verify correct
output
---------
Signed-off-by: betta18 <jiangmengyu1@huawei.com>
Signed-off-by: jiangmengyu18 <56633611+jiangmengyu18@users.noreply.github.com>
Co-authored-by: betta18 <jiangmengyu1@huawei.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
### What this PR does / why we need it?
1. Add version notes for GLM5.
2. Add paramter modification for GLM5.
3. Add GLM5 to supported model list.
### Does this PR introduce _any_ user-facing change?
### How was this patch tested?
- vLLM version: v0.18.0
- vLLM main:
35141a7eed
---------
Signed-off-by: yydyzr <liuyuncong1@huawei.com>
Signed-off-by: Zhu Jiyang <zhujiyang2@huawei.com>
Co-authored-by: Zhu Jiyang <zhujiyang2@huawei.com>
### What this PR does / why we need it?
Qwen3vl full attention supports enabling the split_qkv_rmsnorm_mrope
fusion operator.
### Does this PR introduce _any_ user-facing change?
### How was this patch tested?
- [x] Run Qwen3-VL dense model with the fusion operator, verify correct
output
- [x] Run Qwen3-VL MoE model with the fusion operator, verify correct
output
---------
Signed-off-by: jiangmengyu18 <451528648@qq.com>
Signed-off-by: jiangmengyu18 <56633611+jiangmengyu18@users.noreply.github.com>
Signed-off-by: betta18 <jiangmengyu1@huawei.com>
Co-authored-by: betta18 <jiangmengyu1@huawei.com>
### What this PR does / why we need it?
This PR updates the GLM-5 documentation to include:
- Information about the first supported version
(`vllm-ascend:v0.17.0rc1`).
- Updated `--additional-config` parameters to use the new nested
`ascend_compilation_config` structure.
- Added `VLLM_ASCEND_BALANCE_SCHEDULING` environment variable to
deployment scripts.
- Improved formatting of deployment steps.
- A new "Notice" section explaining optimization environment variables
(`VLLM_ASCEND_ENABLE_FLASHCOMM1`, `VLLM_ASCEND_ENABLE_FUSED_MC2`,
`VLLM_ASCEND_ENABLE_MLAPO`).
- A "Best Practices" section for prefill-decode disaggregation.
- An "FAQ" section addressing common tokenizer issues and function
calling configuration.
### Does this PR introduce _any_ user-facing change?
No, this is a documentation-only update.
### How was this patch tested?
Documentation changes were verified for correctness and formatting.
---------
Signed-off-by: Zhu Jiyang <zhujiyang2@huawei.com>
### What this PR does / why we need it?
Update docs of Kimi-K2.5 for 0.18.0rc1
backport of #7901
---------
Signed-off-by: LoganJane <loganJane73@hotmail.com>
### What this PR does / why we need it?
This PR fixes a weight loading error in the Qwen3-VL model.
The bug was introduced by vLLM. In vLLM's `qwen3-vl.py`, the prefix of
the `lm_head` layer is hardcoded as `"lm_head"`. However,
`hf_to_vllm_mapper` remaps the weight name of `lm_head` from `lm_head`
to `language_model.lm_head`.
This causes a mismatch between the keys in the weight file and the
prefix of the lm_head layer, resulting in an error.
### Does this PR introduce _any_ user-facing change?
### How was this patch tested?
- [x] Run Qwen3-VL dense model with the fusion operator, verify correct
output
Signed-off-by: betta18 <jiangmengyu1@huawei.com>
Co-authored-by: betta18 <jiangmengyu1@huawei.com>
<!-- Thanks for sending a pull request!
BEFORE SUBMITTING, PLEASE READ
https://docs.vllm.ai/en/latest/contributing/overview.html
-->
### What this PR does / why we need it?
vLLM v0.18 defers KV connector finalization during target-modelforward
when speculative decoding is enable, leading to KV Pool not doing Put
Operation. This change is forgotten when we bumpped up the version for
vllm-ascend. Fix by adding finalize_kv_connector for spec decode.
<!--
- Please clarify what changes you are proposing. The purpose of this
section is to outline the changes and how this PR fixes the issue.
If possible, please consider writing useful notes for better and faster
reviews in your PR.
- Please clarify why the changes are needed. For instance, the use case
and bug description.
- Fixes #
-->
### Does this PR introduce _any_ user-facing change?
<!--
Note that it means *any* user-facing change including all aspects such
as API, interface or other behavior changes.
Documentation-only updates are not considered user-facing changes.
-->
### How was this patch tested?
<!--
CI passed with new added/existing test.
If it was tested in a way different from regular unit tests, please
clarify how you tested step by step, ideally copy and paste-able, so
that other reviewers can test and check, and descendants can verify in
the future.
If tests were not added, please describe why they were not added and/or
why it was difficult to add.
-->
Signed-off-by: Pz1116 <zpbzpb123123@gmail.com>
Co-authored-by: DreamerLeader <2270923832@qq.com>
Co-authored-by: fems14 <1804143737@qq.com>
### What this PR does / why we need it?
Fixed the bug of incorrect reshape usage.
For example:
ori_tensor: [[1, 2, 3], [4, 5, 6]]
after reshape:
[[1, 2], [3, 4], [5, 6]]
after permute:
[[1, 4], [2, 5], [3, 6]]
Now, we will directly use squeeze for a more intuitive understanding.
pr for main:
#7887
### Does this PR introduce _any_ user-facing change?
The actual peak-to-average ratio has successfully decreased.
Signed-off-by: shenchuxiaofugui <1311027364@qq.com>
### What this PR does / why we need it?
This PR upgrades the `torch_npu` (PTA) version in multiple Dockerfiles
to a pre-release build. It introduces logic to dynamically select the
correct wheel based on the Python version and system architecture.
### Does this PR introduce _any_ user-facing change?
No.
### How was this patch tested?
CI passed with existing tests. The author should verify that the Docker
images build successfully for all supported architectures and Python
versions.
---------
Signed-off-by: wangli <wangli858794774@gmail.com>
## What this PR does / why we need it?
pick-from:https://github.com/vllm-project/vllm-ascend/pull/7452
### Problem
Embedding models produce inconsistent outputs when prefix caching is
enabled vs disabled.
### Root Cause
The attention router condition was too broad:
- All `model_runner_type == "pooling"` → `_forward_encoder_attention()`
→ uses `npu_fusion_attention`
- **But `npu_fusion_attention` does NOT support prefix caching**
- Result: Numerical mismatch when KV cache is managed by prefix caching
### Solution
Refine the router condition to check causality:
**Before**:
```
if attn_metadata.model_runner_type == "pooling":
→ npu_fusion_attention (no prefix caching support)
```
**After**:
```
if attn_metadata.model_runner_type == "pooling" and not attn_metadata.causal:
→ npu_fusion_attention (for true encoders)
else:
→ npu_fused_infer_attention_score (prefix caching support)
```
### Changes Made
1. **Fixed router condition** (`vllm_ascend/attention/attention_v1.py`
L968)
- Added `and not attn_metadata.causal` check
- Effect: Non-causal embeddings now use correct operator
2. **Simplified encoder attention**
(`vllm_ascend/attention/attention_v1.py` L864-877)
- Removed redundant causal branch (encoders never use causal mask)
- Reduced from 34 lines to 14 lines
3. **Added test** (`tests/e2e/singlecard/pooling/test_embedding.py`)
- Validates embedding outputs with/without prefix caching are consistent
## Does this PR introduce _any_ user-facing change?
### Functional Changes
✅ **Yes** - Bug fix: Embedding models now produce consistent outputs
with prefix caching
### API Changes
❌ **No** - All public APIs unchanged
### Configuration Changes
❌ **No** - No new configuration required
### Backward Compatibility
✅ **Fully compatible** - Only fixes incorrect behavior
## How was this patch tested?
### New Test
Added `test_embed_models_using_prefix_caching_correctness()`:
- Tests: `Qwen3-Embedding-0.6B`
- Validates numerical consistency between runs with/without prefix
caching
- Uses long sequences to activate prefix caching
- Tolerance: 1e-2
- vLLM version: v0.18.0
Signed-off-by: underfituu <hzhucong@163.com>
### What this PR does / why we need it?
This PR backports the `numactl` Docker image update from #7870 to
`releases/v0.18.0`. It installs the `numactl` runtime package in both
Ubuntu-based and openEuler-based Dockerfiles while keeping the existing
development packages (`libnuma-dev` and `numactl-devel`) unchanged.
Backport of #7870.
### Does this PR introduce _any_ user-facing change?
No.
### How was this patch tested?
CI passed in #7870 on `main`. This backport reuses the same
Dockerfile-only change, and no additional local test was run in this
environment.
Signed-off-by: chenchuw886 <chenchuw@huawei.com>
Co-authored-by: chenchuw886 <chenchuw@huawei.com>
### What this PR does / why we need it?
Fix the OOM (Out-of-Memory) error in the single-node-deepseek-v3-2-w8a8
nightly test of vllm-ascend:
- Reduced the value of HCCL_BUFFSIZE
- Lowered the gpu-memory-utilization
Optimize service-side performance:
Updated service-oriented configuration parameters (e.g., max-num-seqs,
cudagraph_capture_sizes, batch_size) to improve the inference
performance,so that the performance is closer to the optimal performance
of the current mainline.
Align performance baseline with main branch:
Updated the performance baseline according to the latest performance
data
### Does this PR introduce _any_ user-facing change?
No.
### How was this patch tested?
The test has passed.
https://github.com/vllm-project/vllm-ascend/actions/runs/23734079080/job/69134387320?pr=7793
---------
Signed-off-by: wyh145 <1987244901@qq.com>
### What this PR does / why we need it?
Due to the current dcp solution of allgathering the KV cache, the
performance deteriorates significantly, and the CI may get stuck. This
PR temporarily removes the performance and accuracy benchmarks for
DeepSeek-V3.2-W8A8-cp to prevent CI hangs until optimization is
complete.
pcik-from:https://github.com/vllm-project/vllm-ascend/pull/7842
### Does this PR introduce _any_ user-facing change?
No
### How was this patch tested?
Verified that the configuration file remains valid and that the CI no
longer attempts to run the problematic benchmarks.
pick-from: https://github.com/vllm-project/vllm-ascend/pull/7842
---------
Signed-off-by: weiguihua2 <weiguihua2@huawei.com>
### What this PR does / why we need
Fix layerwise connector out of memory during large buffer transfer.
### Does this PR introduce _any_ user-facing change?
No.
### How was this patch tested?
By nightly.
---------
Signed-off-by: nwpu-zxr <zhouxuerong2@huawei.com>
Signed-off-by: Mengqing Cao <cmq0113@163.com>
Co-authored-by: Mengqing Cao <cmq0113@163.com>
### What this PR does / why we need it?
This PR fixs accuracy bug in some cases with additional communication
methods.
This PR is a specific fix for version 0.18.0
### Does this PR introduce _any_ user-facing change?
N/A
### How was this patch tested?
CI passed with new added/existing test.
- vLLM version: v0.18.0
- vLLM main:
35141a7eed
---------
Signed-off-by: rjg-lyh <1318825571@qq.com>
Signed-off-by: yydyzr <liuyuncong1@huawei.com>
Co-authored-by: rjg-lyh <1318825571@qq.com>
<!-- Thanks for sending a pull request!
BEFORE SUBMITTING, PLEASE READ
https://docs.vllm.ai/en/latest/contributing/overview.html
-->
### What this PR does / why we need it?
Before when we do put for KV Pool, we find the first non-existing key
and put all the blocks starting from that index; however, if the prefix
cache blocks is from another request, and some of the blocks are evicted
due to LRU, we will be putting blocks that still exist in the pool, and
causing MooncakeStore printing unnecessary logs in master service.
What this PR does:
Now we lookup all the keys and only put the ones that are missing.
Fix lookup_scheduler in pool_worker so it handles GQA correctly.
Fixes a few existing typos
Add UT, written by codex
<!--
- Please clarify what changes you are proposing. The purpose of this
section is to outline the changes and how this PR fixes the issue.
If possible, please consider writing useful notes for better and faster
reviews in your PR.
- Please clarify why the changes are needed. For instance, the use case
and bug description.
- Fixes #
-->
### Does this PR introduce _any_ user-facing change?
<!--
Note that it means *any* user-facing change including all aspects such
as API, interface or other behavior changes.
Documentation-only updates are not considered user-facing changes.
-->
### How was this patch tested?
<!--
CI passed with new added/existing test.
If it was tested in a way different from regular unit tests, please
clarify how you tested step by step, ideally copy and paste-able, so
that other reviewers can test and check, and descendants can verify in
the future.
If tests were not added, please describe why they were not added and/or
why it was difficult to add.
-->
---------
Signed-off-by: Pz1116 <zpbzpb123123@gmail.com>
Co-authored-by: DreamerLeader <2270923832@qq.com>
Co-authored-by: fems14 <1804143737@qq.com>
<!-- Thanks for sending a pull request!
BEFORE SUBMITTING, PLEASE READ
https://docs.vllm.ai/en/latest/contributing/overview.html
-->
### What this PR does / why we need it?
- Add `default_kv_lease_ttl` to the `mooncake.json` example in the KV
Pool guide.
- Document `default_kv_lease_ttl` semantics and clarify that it should
be larger than `ASCEND_CONNECT_TIMEOUT` and `ASCEND_TRANSFER_TIMEOUT`.
- Add `HCCL_RDMA_TIMEOUT` explanation for Mooncake RDMA retransmission
timeout, including the recommended constraint note.
- Add `HCCL_RDMA_TIMEOUT=16` to relevant KV Pool environment setup
examples for consistency.
<!--
- Please clarify what changes you are proposing. The purpose of this
section is to outline the changes and how this PR fixes the issue.
If possible, please consider writing useful notes for better and faster
reviews in your PR.
- Please clarify why the changes are needed. For instance, the use case
and bug description.
- Fixes #
-->
### Does this PR introduce _any_ user-facing change?
<!--
Note that it means *any* user-facing change including all aspects such
as API, interface or other behavior changes.
Documentation-only updates are not considered user-facing changes.
-->
### How was this patch tested?
<!--
CI passed with new added/existing test.
If it was tested in a way different from regular unit tests, please
clarify how you tested step by step, ideally copy and paste-able, so
that other reviewers can test and check, and descendants can verify in
the future.
If tests were not added, please describe why they were not added and/or
why it was difficult to add.
-->
---------
Signed-off-by: Pz1116 <zpbzpb123123@gmail.com>
**What this PR does / why we need it?**
pick from https://github.com/vllm-project/vllm-ascend/pull/7114
Fix compilation errors encountered when building versions later than
b020 for the following operators:
dispatch_gmm_combine_decode, moe_combine_normal, moe_dispatch_normal
**Root Cause**
After the b020 version update, the original moe_distribute_base.h file
was updated and its definitions changed, which caused compilation
failures for the above three operators that depend on this file.
**Solution**
We have added a dedicated copy of moe_distribute_base.h into the
implementation of these three operators, ensuring stable compilation
independent of framework version updates.
**Does this PR introduce any user-facing change?**
No. There are no user-facing changes; this fix only resolves compilation
issues without affecting functionality or user behavior.
**How was this patch tested?**
vLLM version: releases/v0.18.0
Signed-off-by: Wangyibo1005 <2633333316@qq.com>
### What this PR does / why we need it?
Implement get_token_bin_counts_and_mask and apply_penalties with
Triton-Ascend kernels. This significantly reduces latency of the
sampling process when repetition/frequency/presence penalties are
enabled.
Cherry-pick from main PR #7569
### Does this PR introduce _any_ user-facing change?
No.
### How was this patch tested?
CI passed.
Signed-off-by: linfeng-yuan <1102311262@qq.com>
Co-authored-by: realliujiaxu <realliujiaxu@163.com>
### What this PR does / why we need it?
Adjust request map pop time.This pull request optimizes the KV cache
transfer mechanism by streamlining how requests are tracked and cleaned
up. By removing unnecessary mapping structures and adjusting the timing
of request removal, the system achieves more efficient state management
during the transfer process.
pick-from:https://github.com/vllm-project/vllm-ascend/pull/7855
### How was this patch tested?
By ci
<!--
CI passed with new added/existing test.
If it was tested in a way different from regular unit tests, please
clarify how you tested step by step, ideally copy and paste-able, so
that other reviewers can test and check, and descendants can verify in
the future.
If tests were not added, please describe why they were not added and/or
why it was difficult to add.
-->
Signed-off-by: wangxiaoteng <wangxiaoteng@huawei.com>
## Summary
- replace the MiniMax usage accounting monkey patch with a runtime
wrapper implementation instead of source-text rewriting
- preserve MiniMax reasoning-token semantics when `</think>` is missing
by counting the emitted output as reasoning tokens
- add unit coverage for usage tracking helpers and MiniMax
reasoning-token counting
## Why
The previous implementation rewrote `OpenAIServingChat` by matching
exact source blocks. That was brittle against `vllm` source drift and
could crash during early plugin initialization with:
`RuntimeError: Failed to locate expected block while patching
OpenAIServingChat usage accounting.`
This change keeps the usage-accounting backport, but applies it by
wrapping the original stream/full generators and tracking output token
ids at runtime.
For MiniMax reasoning counting, a missing `</think>` should not be
treated as zero reasoning tokens. It can mean the whole output is still
in thinking mode, or that generation stopped before the closing token
was produced. In that case, the emitted output should still be counted
as reasoning.
## Validation
- `pytest -q
tests/ut/patch/platform/test_patch_minimax_usage_accounting.py`
- `vllm serve --help`
Signed-off-by: QwertyJack <7554089+QwertyJack@users.noreply.github.com>
Co-authored-by: QwertyJack <7554089+QwertyJack@users.noreply.github.com>
### What this PR does / why we need it?
Optimize DeepSeekOCR2 RelPosAttention and CustomQwen2Decoder and add doc
for DeepSeekOCR2.md
### Does this PR introduce _any_ user-facing change?
### How was this patch tested?
- vllm 0.18.0
- vllm-ascend main
1. _create_custom_4d_mask during 141ms49us620ns -->
_create_npu_optimized_mask during 1ms227us780ns
2. convd2d : 27ms --> matmul <1ms
3. relposattention：sdpa->prompt_flash_attention
---------
Signed-off-by: Wangbei25 <wangbei41@huawie.com>
Signed-off-by: Wangbei25 <wangbei41@huawei.com>
Co-authored-by: Wangbei25 <wangbei41@huawie.com>
…(#7603)
### What this PR does / why we need it?
Block verify uses cumprod(target_probs / draft_probs) for joint
acceptance. Suffix/ngram methods have
draft_probs=None, the fallback draft_token_probs=1.0 with cumprod is not
equivalent to per-token
verification, causing incorrect accept/reject results. Fix:
using_block_verify = max_spec_len >= 3 and draft_probs is not None.
MTP/Eagle3 unaffected.
- vLLM version: v0.18.0
- vLLM main:
ed359c497a
<!-- Thanks for sending a pull request!
BEFORE SUBMITTING, PLEASE READ
https://docs.vllm.ai/en/latest/contributing/overview.html
-->
### What this PR does / why we need it?
<!--
- Please clarify what changes you are proposing. The purpose of this
section is to outline the changes and how this PR fixes the issue.
If possible, please consider writing useful notes for better and faster
reviews in your PR.
- Please clarify why the changes are needed. For instance, the use case
and bug description.
- Fixes #
-->
### Does this PR introduce _any_ user-facing change?
<!--
Note that it means *any* user-facing change including all aspects such
as API, interface or other behavior changes.
Documentation-only updates are not considered user-facing changes.
-->
### How was this patch tested?
<!--
CI passed with new added/existing test.
If it was tested in a way different from regular unit tests, please
clarify how you tested step by step, ideally copy and paste-able, so
that other reviewers can test and check, and descendants can verify in
the future.
If tests were not added, please describe why they were not added and/or
why it was difficult to add.
-->
Signed-off-by: liuchenbing <chenliumail@163.com>
Co-authored-by: liuchenbing <chenliumail@163.com>
