### What this PR does / why we need it?
The attention mechanism in the ViT model architecture of Qwen2.5VL
consists of two parts and does not support using cache to pass sequence
lengths.
### Does this PR introduce _any_ user-facing change?
remove seq_lens_cache
### How was this patch tested?
- vLLM version: v0.16.0
- vLLM main:
15d76f74e2
---------
Signed-off-by: tanhaoan333 <tanhaoan@huawei.com>
### What this PR does / why we need it?
Currently, the performance of multi-modal encoding (i.e.,
`AscendMMEncoderAttention` forward) is considerably bounded by the heavy
host pre-process operations.
We can see from the profiling results below, before the real computation
of Attention, there are long free time in the device, which will lead to
extremely low NPU utilization.
<img width="2264" height="1398" alt="iShot_2026-01-23_16 26 39"
src="https://github.com/user-attachments/assets/37f21d06-e526-4f28-82fe-005746cf13bd"
/>
---
**To opitimize this, this PR has proposed four changes:**
1. Use `seq_lens` CPU cache to avoid frequent d2h copy. Before this PR,
`AscendMMEncoderAttention` will copy the `cu_seqlens` from NPU to CPU in
every forward, since the op `_npu_flash_attention_unpad()` requires CPU
`cu_seqlens` (otherwise it will crash). Thus, we use
`seq_lens_cpu_cache` to cache this tensor, since it's shared between all
layers, but may change in different forward step. When the current
`layer_index` is `0`, we update the cache, otherwise we directly use the
cache to avoid frequent `diff` and `copy` operations, which are costful.
2. Pre-compute the scale value to avoid calculating it in every forward.
3. Move the judgment of `enable_pad` from forward to the `__init__`
method.
4. Revert https://github.com/vllm-project/vllm-ascend/pull/6204.
**Performance after these optimizations:**
- **TTFT** has been reduced by **7.43%** ⬇️.
- **Throughput** has been increased by **1.23%** ⬆️.
---
> [!NOTE]
> This PR requires https://github.com/vllm-project/vllm/pull/33674 be
merged.
---
### Does this PR introduce _any_ user-facing change?
No.
### How was this patch tested?
Launch the server:
```bash
vllm serve /root/.cache/modelscope/hub/models/Qwen/Qwen3-VL-8B-Instruct \
--dtype bfloat16 \
--limit-mm-per-prompt '{"image": 1}' \
--max-model-len 16384 \
--max-num-batched-tokens 16384 \
--no-async-scheduling
```
Run benchmark:
```bash
vllm bench serve \
--model /root/.cache/modelscope/hub/models/Qwen/Qwen3-VL-8B-Instruct \
--backend openai-chat \
--endpoint /v1/chat/completions \
--dataset-name hf \
--hf-split train \
--dataset-path lmarena-ai/vision-arena-bench-v0.1 \
--num-prompts 500 \
--request-rate 10 \
--burstiness 5 \
--no-stream
```
Before this PR:
```
============ Serving Benchmark Result ============
Successful requests: 500
Failed requests: 0
Request rate configured (RPS): 10.00
Benchmark duration (s): 82.23
Total input tokens: 33418
Total generated tokens: 61543
Request throughput (req/s): 6.08
Output token throughput (tok/s): 748.45
Peak output token throughput (tok/s): 3203.00
Peak concurrent requests: 402.00
Total token throughput (tok/s): 1154.86
---------------Time to First Token----------------
Mean TTFT (ms): 10275.37
Median TTFT (ms): 6297.88
P99 TTFT (ms): 22918.26
-----Time per Output Token (excl. 1st token)------
Mean TPOT (ms): 263.02
Median TPOT (ms): 277.61
P99 TPOT (ms): 483.56
---------------Inter-token Latency----------------
Mean ITL (ms): 257.31
Median ITL (ms): 94.83
P99 ITL (ms): 1773.90
==================================================
```
After this PR:
```
============ Serving Benchmark Result ============
Successful requests: 500
Failed requests: 0
Request rate configured (RPS): 10.00
Benchmark duration (s): 81.20
Total input tokens: 33418
Total generated tokens: 61509
Request throughput (req/s): 6.16
Output token throughput (tok/s): 757.54
Peak output token throughput (tok/s): 2562.00
Peak concurrent requests: 395.00
Total token throughput (tok/s): 1169.11
---------------Time to First Token----------------
Mean TTFT (ms): 9511.91
Median TTFT (ms): 5479.78
P99 TTFT (ms): 21427.21
-----Time per Output Token (excl. 1st token)------
Mean TPOT (ms): 261.12
Median TPOT (ms): 276.03
P99 TPOT (ms): 446.99
---------------Inter-token Latency----------------
Mean ITL (ms): 254.04
Median ITL (ms): 97.71
P99 ITL (ms): 1516.67
==================================================
```
- vLLM version: v0.15.0
- vLLM main:
dc917cceb8
Signed-off-by: shen-shanshan <467638484@qq.com>
### What this PR does / why we need it?
This PR upgrades the vLLM dependency from `v0.14.1` to `v0.15.0`. This
involves:
- Updating the `VLLM_TAG` in all `Dockerfile`.
- Updating the vLLM version in `docs/source/conf.py`.
- Removing conditional code paths specific to `v0.14.1` across the
codebase, which simplifies maintenance.
- Fix `TypeError: MMEncoderAttention.__init__() got an unexpected
keyword argument 'multimodal_config'` due to
https://github.com/vllm-project/vllm/pull/31972.
- Fix `_shared_experts: 'NoneType' object is not callable` due to
https://github.com/vllm-project/vllm/pull/32082 by
https://github.com/vllm-project/vllm-ascend/pull/6335.
- Fix `ReshapeAndCacheOperation setup failed!` due to
https://github.com/vllm-project/vllm/pull/25954 by overriding attention
metadata slots.
This upgrade is necessary to keep the project aligned with the latest
features, bug fixes, and API changes in the vLLM project.
### Does this PR introduce _any_ user-facing change?
No, this is an internal dependency update and does not introduce any
user-facing changes.
### How was this patch tested?
CI is expected to pass with these changes, ensuring that all existing
tests are successful with the new vLLM version.
- vLLM version: v0.14.1
- vLLM main:
dc917cceb8
co-authored-by: shen-shanshan <467638484@qq.com>
---------
Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
### What this PR does / why we need it?
Currently, we pad the last dim of qkv to 128 before flash attention (in
`AscendMMEncoderAttention`) to get better performance on Ascend NPU.
However, the qkv padding is executed serially, which may lead to more
overhead when launching `aclnnConstantPadNd` (launch 3 times).
Since the three operations are mutually independent, we stack qkv first
and then pad them in one kernel launch. With this optimization, **TTFT**
has been reduced by **3.15%**, **peak throughput** has been increased by
**4.20%**.
---
### Does this PR introduce _any_ user-facing change?
No.
### How was this patch tested?
Launch the server:
```bash
vllm serve /root/.cache/modelscope/hub/models/Qwen/Qwen3-VL-8B-Instruct \
--dtype bfloat16 \
--limit-mm-per-prompt '{"image": 1}' \
--max-model-len 16384 \
--max-num-batched-tokens 16384
```
Run benchmark:
```bash
vllm bench serve \
--model /root/.cache/modelscope/hub/models/Qwen/Qwen3-VL-8B-Instruct \
--backend openai-chat \
--endpoint /v1/chat/completions \
--dataset-name hf \
--hf-split train \
--dataset-path lmarena-ai/vision-arena-bench-v0.1 \
--num-prompts 1000 \
--no-stream
```
Before this PR:
```
============ Serving Benchmark Result ============
Successful requests: 1000
Failed requests: 0
Benchmark duration (s): 122.33
Total input tokens: 66638
Total generated tokens: 122845
Request throughput (req/s): 8.17
Output token throughput (tok/s): 1004.18
Peak output token throughput (tok/s): 3073.00
Peak concurrent requests: 1000.00
Total token throughput (tok/s): 1548.90
---------------Time to First Token----------------
Mean TTFT (ms): 51757.16
Median TTFT (ms): 44853.42
P99 TTFT (ms): 110700.14
-----Time per Output Token (excl. 1st token)------
Mean TPOT (ms): 226.06
Median TPOT (ms): 206.85
P99 TPOT (ms): 935.31
---------------Inter-token Latency----------------
Mean ITL (ms): 208.82
Median ITL (ms): 96.37
P99 ITL (ms): 2183.13
==================================================
```
After this PR:
```
============ Serving Benchmark Result ============
Successful requests: 1000
Failed requests: 0
Benchmark duration (s): 121.47
Total input tokens: 66638
Total generated tokens: 122860
Request throughput (req/s): 8.23
Output token throughput (tok/s): 1011.47
Peak output token throughput (tok/s): 3202.00
Peak concurrent requests: 1000.00
Total token throughput (tok/s): 1560.08
---------------Time to First Token----------------
Mean TTFT (ms): 50125.08
Median TTFT (ms): 46270.85
P99 TTFT (ms): 108107.12
-----Time per Output Token (excl. 1st token)------
Mean TPOT (ms): 227.11
Median TPOT (ms): 205.13
P99 TPOT (ms): 816.08
---------------Inter-token Latency----------------
Mean ITL (ms): 204.60
Median ITL (ms): 92.66
P99 ITL (ms): 2219.02
==================================================
```
- vLLM version: v0.14.0
- vLLM main:
d68209402d
Signed-off-by: shen-shanshan <467638484@qq.com>
### What this PR does / why we need it?
Drop vLLM 0.13.0 support, upgrade to 0.14.0
- vLLM version: v0.13.0
- vLLM main:
d68209402d
---------
Signed-off-by: hfadzxy <starmoon_zhang@163.com>
### What this PR does / why we need it?
### Does this PR introduce _any_ user-facing change?
Fix vllm break:
1. [Enable cuda graph for deepepHT, 5.3% throughput improvement, 4.4%
TTFT improvement] (https://github.com/vllm-project/vllm/pull/29558)
Fix Solution: Add the now-necessary `all2all_backend` parameter. The
impact of this parameter on the original `set_splitting_ops_for_v1`
implementation is only that graph mode is disabled in `vllm` if
`deepep_high_throughput` is enabled; it has no effect on the
`vllm-ascend` logic.
2.[Migrate legacy ViT MultiHeadAttention to new MMEncoderAttention
interface ] (https://github.com/vllm-project/vllm/pull/30684)
Fix Solution: The reason why the GPU does not need to convert qkv to 3D
is that the GPU's flash_attention operator is compatible with 3D and 4D
(b s h d and s b ( h d)), but the NPU's flash_attention_unpad operator
only supports 3D (s b ( h d)). Therefore, we need to introduce the
reshape_qkv_to_3d operation.
4.Skip Tencent-Hunyuan/HunyuanOCR test case, as it has following issue
in upgrade vllm code:
https://github.com/vllm-project/vllm-ascend/issues/5297
### How was this patch tested?
Co-authored-by: zxwang <1476209578@qq.com>
- vLLM version: release/v0.13.0
- vLLM main:
ad32e3e19c
---------
Signed-off-by: leo-pony <nengjunma@outlook.com>
Signed-off-by: zxwang <1476209578@qq.com>
Co-authored-by: zxwang <1476209578@qq.com>
### What this PR does / why we need it?
Following https://github.com/vllm-project/vllm/pull/29873, register
`AscendApplyRotaryEmb` CustomOp and remove related patch.
### Does this PR introduce _any_ user-facing change?
### How was this patch tested?
#### ✅ Test Qwen2.5-VL
Run:
```bash
vllm serve /root/.cache/modelscope/hub/models/Qwen/Qwen2.5-VL-7B-Instruct \
--max_model_len 16384
```
Output:
```
{"id":"chatcmpl-b02c1ff3415d2462","object":"chat.completion","created":1766129265,"model":"/root/.cache/modelscope/hub/models/Qwen/Qwen2.5-VL-7B-In struct","choices":[{"index":0,"message":{"role":"assistant","content":"The text in the illustration is \"TONGYI Qwen.\" The word \"TONGYI\" is writ ten in blue, and \"Qwen\" is written in gray. The text appears to be part of a logo or branding design.","refusal":null,"annotations":null,"audio": null,"function_call":null,"tool_calls":[],"reasoning":null,"reasoning_content":null},"logprobs":null,"finish_reason":"stop","stop_reason":null,"tok en_ids":null}],"service_tier":null,"system_fingerprint":null,"usage":{"prompt_tokens":78,"total_tokens":129,"completion_tokens":51,"prompt_tokens_d
```
#### ✅ Test Qwen3-VL
Run:
```bash
vllm serve /root/.cache/modelscope/hub/models/Qwen/Qwen3-VL-8B-Instruct \
--max_model_len 16384
```
Output:
```
{"id":"chatcmpl-a3a7de5a900a9321","object":"chat.completion","created":1766129586,"model":"/root/.cache/modelscope/hub/models/Qwen/Qwen3-VL-8B-Instruct","choices":[{"index":0,"message":{"role":"assistant","content":"The text in the illustration is **“TONGYI Qwen”**.\n\n### How it looks:\n- **“TONGYI”** is written in **uppercase letters** in a **bold, modern sans-serif font**, colored **blue**.\n- **“Qwen”** is written in **lowercase letters** in a **slightly thinner, elegant sans-serif font**, colored **dark gray**.\n- The two lines of text are stacked vertically, with “TONG","refusal":null,"annotations":null,"audio":null,"function_call":null,"tool_calls":[],"reasoning":null,"reasoning_content":null},"logprobs":null,"finish_reason":"length","stop_reason":null,"token_ids":null}],"service_tier":null,"system_fingerprint":null,"usage":{"prompt_tokens":112,"total_tokens":212,"completion_tokens":100,"prompt_tokens_details":null},"prompt_logprobs":null,"prompt_token_ids":null,"kv_transfer_params":null}
```
- vLLM version: v0.12.0
- vLLM main:
ad32e3e19c
---------
Signed-off-by: shen-shanshan <467638484@qq.com>
### What this PR does / why we need it?
Following https://github.com/vllm-project/vllm/pull/30125, register
`AscendMMEncoderAttention` CustomOp and remove related patch.
### Does this PR introduce _any_ user-facing change?
No.
### How was this patch tested?
✅ Run Qwen2.5-VL:
```bash
vllm serve /root/.cache/modelscope/hub/models/Qwen/Qwen2.5-VL-7B-Instruct \
--max_model_len 16384
```
Output:
```
{"id":"chatcmpl-b4e3053f30ab2442","object":"chat.completion","created":1764922950,"model":"/root/.cache/modelscope/hub/models/Qwen/Qwen2.5-VL-7B-Instruct","choices":[{"index":0,"message":{"role":"assistant","content":"The text in the image is \"TONGYI Qwen.\" The word \"TONGYI\" is written in blue, and \"Qwen\" is written in gray. The font appears to be modern and clean, with \"TONGYI\" being slightly larger than \"Qwen.\" The design includes a geometric, abstract shape on the left side of the logo, which complements the text.","refusal":null,"annotations":null,"audio":null,"function_call":null,"tool_calls":[],"reasoning":null,"reasoning_content":null},"logprobs":null,"finish_reason":"stop","stop_reason":null,"token_ids":null}],"service_tier":null,"system_fingerprint":null,"usage":{"prompt_tokens":78,"total_tokens":162,"completion_tokens":84,"prompt_tokens_details":null},"prompt_logprobs":null,"prompt_token_ids":null,"kv_transfer_params":null}
```
✅ Run Qwen3-VL:
```bash
vllm serve /root/.cache/modelscope/hub/models/Qwen/Qwen3-VL-8B-Instruct \
--max_model_len 16384
```
Output:
```
{"id":"chatcmpl-97571fbda8267bd1","object":"chat.completion","created":1764923306,"model":"/root/.cache/modelscope/hub/models/Qwen/Qwen3-VL-8B-Instruct","choices":[{"index":0,"message":{"role":"assistant","content":"The text in the illustration is **“TONGYI Qwen”**.\n\n### How it looks:\n- **“TONGYI”** is written in **uppercase letters** in a **bold, modern sans-serif font**, colored **blue**.\n- **“Qwen”** is written in **lowercase letters** in a **slightly thinner, elegant sans-serif font**, colored **dark gray**.\n- The two lines of text are stacked vertically, with “TONG","refusal":null,"annotations":null,"audio":null,"function_call":null,"tool_calls":[],"reasoning":null,"reasoning_content":null},"logprobs":null,"finish_reason":"length","stop_reason":null,"token_ids":null}],"service_tier":null,"system_fingerprint":null,"usage":{"prompt_tokens":112,"total_tokens":212,"completion_tokens":100,"prompt_tokens_details":null},"prompt_logprobs":null,"prompt_token_ids":null,"kv_transfer_params":null}
```
- vLLM version: v0.12.0
- vLLM main:
ad32e3e19c
---------
Signed-off-by: shen-shanshan <467638484@qq.com>
Co-authored-by: Yikun Jiang <yikunkero@gmail.com>
