### What this PR does / why we need it?
Overview: This pull request refactors speculative decoding for Eagle and
MTP proposers on Ascend hardware. It fixes a bug related to
draft_attn_metadatas being lost, migrates the lmhead feature, and adds
routing logic in MtpProposer.
Details:
1. Migrated the lmhead feature from mtp to eagle and normalized it in
eagle_proposer.
2. Fixed the bug where draft_attn_metadatas was lost after enabling
eagle mode in the merge graph.
3. Added the routing for pcp and disable padded drafter batch; in mtp
mode, if pcp and disable padded drafter batch are not enabled, the
normalized file eagle_proposer will be used.
RFC: https://github.com/vllm-project/vllm-ascend/issues/5467
### Does this PR introduce _any_ user-facing change?
No
### How was this patch tested?
ut and test
- vLLM version: v0.14.1
- vLLM main:
dc917cceb8
---------
Signed-off-by: lilinsiman <lilinsiman@gmail.com>
### What this PR does / why we need it?
While using the LLM Compressor quantization tool from the VLLM community
to generate quantized weights, the VLLM Ascend engine needs to be
adapted to support the compressed tensors quantization format.
1. Support Moe model W4A8 dynamic weight.
- vLLM version: v0.13.0
- vLLM main:
bde38c11df
---------
Signed-off-by: LHXuuu <scut_xlh@163.com>
Signed-off-by: menogrey <1299267905@qq.com>
Co-authored-by: menogrey <1299267905@qq.com>
### What this PR does / why we need it?
- Replace the RoPE operator implementation.
- Refactor some leftover implementations of 300I DUO in the main branch.
### Does this PR introduce _any_ user-facing change?
NA
### How was this patch tested?
- vLLM version: v0.14.1
- vLLM main:
dc917cceb8
---------
Signed-off-by: Tflowers-0129 <2906339855@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?
**Scope of Changes**:
| File Path |
| :--- |
|`vllm_ascend/worker/model_runner_v1.py`|
|`vllm_ascend/worker/pcp_utils.py`|
### Does this PR introduce _any_ user-facing change?
### How was this patch tested?
- vLLM version: v0.13.0
- vLLM main:
d68209402d
---------
Signed-off-by: MrZ20 <2609716663@qq.com>
### What this PR does / why we need it?
This PR removes the custom `ProfileExecuteDuration` utility and its
usages across the codebase. This utility was used for profiling
execution duration of different stages in the inference process. It is
replaced by the standard `vllm.v1.utils.record_function_or_nullcontext`,
which integrates with PyTorch's profiler.
This change simplifies the code by removing a custom implementation in
favor of an upstream utility, improving maintainability. Associated
documentation and tests for `ProfileExecuteDuration` are also removed.
### Does this PR introduce _any_ user-facing change?
`VLLM_ASCEND_MODEL_EXECUTE_TIME_OBSERVE` env is removed now.
### How was this patch tested?
CI passed. The changes are a cleanup and replacement with a standard
utility. Existing tests cover the functionality. The removed feature had
its own tests which are also removed.
Related RFC: #5304
- vLLM version: v0.14.1
- vLLM main:
dc917cceb8
Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
### What this PR does / why we need it?
There is an issue with the current default logic for MLAPO (MLA Policy
Optimization). By design, MLAPO should only be enabled by default on
Decode (D) nodes. However, in hybrid (collocated prefill and decode)
scenarios, the strategy is erroneously activated during the Prefill
stage.
This PR corrects the default behavior to ensure that MLAPO is
exclusively enabled for the Decoding phase. This prevents unexpected
policy interference during Prefill and ensures optimal performance in
hybrid deployment environments.
### Does this PR introduce _any_ user-facing change?
### How was this patch tested?
- vLLM version: v0.14.1
- vLLM main:
dc917cceb8
---------
Signed-off-by: fems14 <1804143737@qq.com>
This reverts commit 56f5d3bd49.
### What this PR does / why we need it?
The patch https://github.com/vllm-project/vllm-ascend/pull/6357 which
break the functionality availability in the spec_decode scenario, let's
revert and make CI happy first
### Does this PR introduce _any_ user-facing change?
### How was this patch tested?
- vLLM version: v0.14.1
- vLLM main:
dc917cceb8
Signed-off-by: wangli <wangli858794774@gmail.com>
### What this PR does / why we need it?
Since the PR (https://github.com/vllm-project/vllm/pull/32118) has
modified the criteria for judging Prefill and Decode requests in vLLM,
PCPManager needs to synchronize with this standard. As PCPManager
involves multiple calculations of PD request counts, this PR attempts to
consolidate the related logic and update the PD request count once per
batch.
### How was this patch tested?
```bash
pytest tests/e2e/multicard/4-cards/long_sequence/test_mtp.py
```
- vLLM version: v0.13.0
- vLLM main:
11b6af5280
Signed-off-by: QiuChunshuo <qiuchunshuo@huawei.com>
### What this PR does / why we need it?
change self.head_size to self.rotary_dim.
only the rotary part is processed here, the dimension should be rotary_dim.
Fix bug #6060
### Does this PR introduce _any_ user-facing change?
No
### How was this patch tested?
Only a small section of code was modified to adjust the parameters, and
all standard tests were passed.
- vLLM version: v0.14.1
- vLLM main:
dc917cceb8
Signed-off-by: fengshi666 <fengshi666@adsl-99-12-210-25.dsl.hstntx.sbcglobal.net>
Co-authored-by: fengshi666 <fengshi666@adsl-99-12-210-25.dsl.hstntx.sbcglobal.net>
### What this PR does / why we need it?
This handles both uniform and mixed batches (by inserting a dummy
request for mixed batches), consolidates ad-hoc padding into a single
helper, copies the updated buffer to the device, and asserts the layout
constraint before building the attention metadata. Together, these
changes prevent kernel mismatches or failures and ensure correct shapes
for FIA/TND execution in full graph modes.
We currently place this helper in `execute_model`. My original design
was to include it in `_prepare_inputs`, but that doesn’t work because it
must run after padding. While I’d prefer to minimize the impact and
reuse as much of the base class as possible in the future, it doesn’t
seem achievable at the moment.
### Does this PR introduce _any_ user-facing change?
None.
### How was this patch tested?
Test cases added.
- vLLM version: v0.14.1
- vLLM main:
dc917cceb8
---------
Signed-off-by: Yizhou Liu <liu_yizhou@outlook.com>
### What this PR does / why we need it?
Added an E2E test case for the scenario of enabling a static kernel for
npugraph_ex, monitoring its compilation and unloading process.
Also fixed the previously existing spelling errors
- vLLM version: v0.14.1
- vLLM main:
dc917cceb8
---------
Signed-off-by: chencangtao <chencangtao@huawei.com>
Co-authored-by: chencangtao <chencangtao@huawei.com>
### What this PR does / why we need it?
Using the cache load operator to replace the index select operator.
- vLLM version: v0.14.1
- vLLM main:
dc917cceb8
---------
Signed-off-by: liziyu <liziyu16@huawei.com>
### What this PR does / why we need it?
The rope_forward_triton method reports an error.
For example:
```
(Worker_DP0_TP1_EP1 pid=5298) ERROR 01-29 02:01:11 [multiproc_executor.py:822] q, k = rope_forward_triton(q, k, cos, sin, rope_dim=self.qk_rope_head_dim, is_neox_style=True)
(Worker_DP0_TP1_EP1 pid=5298) ERROR 01-29 02:01:11 [multiproc_executor.py:822] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(Worker_DP0_TP1_EP1 pid=5298) ERROR 01-29 02:01:11 [multiproc_executor.py:822] File "/vllm-workspace/vllm-ascend/vllm_ascend/ops/triton/rope.py", line 155, in rope_forward_triton
(Worker_DP0_TP1_EP1 pid=5298) ERROR 01-29 02:01:11 [multiproc_executor.py:822] cos = cos.view(num_tokens, -1)
(Worker_DP0_TP1_EP1 pid=5298) ERROR 01-29 02:01:11 [multiproc_executor.py:822] ^^^^^^^^^^^^^^^^^^^^^^^^
(Worker_DP0_TP1_EP1 pid=5298) ERROR 01-29 02:01:11 [multiproc_executor.py:822] RuntimeError: shape '[14, -1]' is invalid for input of size 768
```
This is because an incorrect num_tokens_padded was passed in.
Related-RFC: https://github.com/vllm-project/vllm-ascend/issues/5449
Co-authored-by: @zhenwenqi2024
### Does this PR introduce _any_ user-facing change?
### How was this patch tested?
- vLLM version: v0.14.1
- vLLM main:
dc917cceb8
Signed-off-by: Wang Kunpeng <1289706727@qq.com>
### What this PR does / why we need it?
We only do restore and recover for pcp, so we should set
`kv_inverse_idx_for_chunk` and `cp_kv_recover_idx_for_chunk` to `None`
when only using dcp.
- vLLM version: v0.14.1
- vLLM main:
dc917cceb8
Signed-off-by: QiuChunshuo <qiuchunshuo@huawei.com>
### What this PR does / why we need it?
PR #5672 attempted to remove the -1 padding for duplicate tokens in the
decode slot_mapping when adapting PCP for MLAPO, and adopted a simpler
slicing approach. However, in the single-ops logic and mixed PD batches,
the decode slot_mapping did not eliminate the -1 and also shared the
slicing method, resulting in incorrect slot_mapping. This PR resolves
this issue, and the logic will be further consolidated in subsequent
refactoring PRs.
- vLLM version: v0.14.1
- vLLM main:
dc917cceb8
---------
Signed-off-by: QiuChunshuo <qiuchunshuo@huawei.com>
### What this PR does / why we need it?
Qwen3-VL-MoE EAGLE support for vLLM-Ascend
### Does this PR introduce _any_ user-facing change?
No
### How was this patch tested?
The patch tested with Qwen3-VL-30B-A3B-Instruct model
- vLLM version: v0.14.1
- vLLM main:
dc917cceb8
Signed-off-by: Sergey_Zlobin <sirg_zlobin@mail.ru>
### What this PR does / why we need it?
This PR fixes a critical bug in the PD-separated inference pipeline
where KV cache on the Prefill (P) side was not being properly released.
The issue arises when multiple clients use the same x-request-id: to
avoid request ID collisions, both Prefill and Decode nodes append a
random suffix to the incoming x-request-id. A previous PR ensured
consistency by having the P-side pass its final request_id as
remote_request_id to the D-side via kv_transfer_param. However, during
KV cache cleanup, the D-side incorrectly used the local req_id (instead
of remote_request_id) to select the target P-side rank. This mismatch
caused the P-side KV cache to remain unreleased on certain ranks,
leading to memory leaks. This PR corrects the logic to use
remote_request_id consistently when determining the P-side rank.
### Does this PR introduce _any_ user-facing change?
No.
### How was this patch tested?
The fix was validated by running multiple concurrent benchmark instances
- vLLM version: v0.14.1
- vLLM main:
dc917cceb8
Signed-off-by: ghphotoframe <854746559@qq.com>
We patched deepseek before since we notice asserterror raised by
transformers. Now due to transformers upgrade, the patch looks useless
now. Let's remove it.
- vLLM version: v0.14.1
- vLLM main:
dc917cceb8
Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
### What this PR does / why we need it?
PR https://github.com/vllm-project/vllm/pull/32082 in vLLM makes
Qwen3-Moe models also go into `SharedFusedMoE`, while current
implementation of our `AscendSharedFusedMoE` assumes shared_experts
always exist. This PR adds checking to
`multistream_overlap_shared_expert` and `multistream_overlap_gate` in
order to only enable these features when shared experts exist.
### Does this PR introduce _any_ user-facing change?
No
### How was this patch tested?
All ci passed
- vLLM version: v0.14.1
- vLLM main:
dc917cceb8
Signed-off-by: whx-sjtu <2952154980@qq.com>
### What this PR does / why we need it?
Disable enable_shared_expert_dp by default if tensor_parallel_size=1
- vLLM version: v0.14.1
- vLLM main:
dc917cceb8
Signed-off-by: underfituu <hzhucong@163.com>
### What this PR does / why we need it?
This PR rebases RecomputeScheduler codebase to vllm tags/v0.14.1 in
order to fix the incompatibility with vllm's original Scheduler and
AsyncScheduler. Main changes focus on multimodal model and speculative
decoding parts.
### Does this PR introduce _any_ user-facing change?
No.
### How was this patch tested?
We tested this PR with 2P1D E2E serving test case.
- vLLM version: v0.14.1
- vLLM main:
d68209402d
---------
Signed-off-by: linfeng-yuan <1102311262@qq.com>
### What this PR does / why we need it?
Adds a CUDA graph profiling stats field to the execution state and
updates the NPU model runner to set, unpack, and forward those stats
during execution. This preserves CUDA graph metrics across state
transitions, improving observability for later use and diagnostics.
### Does this PR introduce _any_ user-facing change?
Enable this by set
```python
llm = LLM(
...
disable_log_stats=False,
cudagraph_metrics=True,
...
)
```
or `--cudagraph-metrics` and make sure do not disable log stats.
After this, you should be able to see something like this, which is
really helpful for some light debugging:
```
[loggers.py:257] Engine 000: Avg prompt throughput: 32.3 tokens/s, Avg generation throughput: 114.4 tokens/s, Running: 4 reqs, Waiting: 0 reqs, GPU KV cache usage: 0.1%, Prefix cache hit rate: 0.0%
[cuda_graph.py:117] **CUDAGraph Config Settings:**
[cuda_graph.py:117]
[cuda_graph.py:117] - Mode: FULL_DECODE_ONLY
[cuda_graph.py:117] - Capture sizes: [1, 2, 4, 8, 16, 24, 32]
[cuda_graph.py:117]
[cuda_graph.py:117] **CUDAGraph Stats:**
[cuda_graph.py:117]
[cuda_graph.py:117] | Unpadded Tokens | Padded Tokens | Num Paddings | Runtime Mode | Count |
[cuda_graph.py:117] |-----------------|---------------|--------------|--------------|-------|
[cuda_graph.py:117] | 4 | 4 | 0 | FULL | 18 |
[cuda_graph.py:117] | 5 | 5 | 0 | NONE | 1 |
[cuda_graph.py:117] | 1 | 1 | 0 | FULL | 1 |
[cuda_graph.py:117] | 18 | 18 | 0 | NONE | 1 |
```
### How was this patch tested?
None.
- vLLM version: v0.14.1
- vLLM main:
dc917cceb8
Signed-off-by: Yizhou Liu <liu_yizhou@outlook.com>
### What this PR does / why we need it?
Fix the MTP test failure caused by accessing non-existent attribute
`forward_context.draft_attn_metadatas`.
**Root cause:**
In `AscendAttentionBackendImpl.update_graph_params`, the code
incorrectly accessed `forward_context.draft_attn_metadatas`, but
`ForwardContext` class doesn't have this attribute. The original code
passed this value via function parameter.
**Fix:**
Add `draft_attn_metadatas` parameter to the entire call chain:
- `update_full_graph_params` function in `acl_graph.py`
- All `update_graph_params` methods in attention backends
- Pass the parameter correctly in `eagle_proposer.py`
Also applied Gemini's suggestion to make `vllm_config=None` in
`AscendAttentionCPImpl.update_graph_params` for API consistency.
Related to item 9 in #5463
### Does this PR introduce _any_ user-facing change?
No.
### How was this patch tested?
This fixes the CI test failure:
`test_deepseek_mtp_correctness[True-FULL_DECODE_ONLY-2-wemaster/deepseek_mtp_main_random_bf16]`
Signed-off-by: lico67373 <918688502@qq.com>
### What this PR does / why we need it?
The structure of the `excute_model` and `_dymmy_run` methods in
NPUModelRunner differs greatly from that in GPUModelRunner.
Achieve alignment with GPUModelRunner:
Split the `_prepare_inputs` method into `_prepare_inputs`,
`_determine_batch_execution_and_padding`, `_build_attention_metadata`,
and `_preprocess`.
Modify `_generate_process_reqs_hidden_states` to `_model_forward`.
Align the implementation of the `postprocess` phase
**Related-RFC**: https://github.com/vllm-project/vllm-ascend/issues/5449
**Co-authored-by**: @zhenwenqi2024
### Does this PR introduce _any_ user-facing change?
no
### How was this patch tested?
- vLLM version: v0.13.0
- vLLM main:
d68209402d
---------
Signed-off-by: Wang Kunpeng <1289706727@qq.com>
Signed-off-by: gcanlin <canlinguosdu@gmail.com>
Signed-off-by: zhenwenqi2024 <zhenwenqi_2022@qq.com>
Co-authored-by: gcanlin <canlinguosdu@gmail.com>
Co-authored-by: zhenwenqi2024 <zhenwenqi_2022@qq.com>
### What this PR does / why we need it?
This PR optimizes the torch_npu profiler configuration to significantly
reduce overhead and trace file size. The key changes include:
**Enable Data Simplification**: Explicitly sets data_simplification=True
in _ExperimentalConfig. This filters out unnecessary intermediate data
during profiling, drastically reducing the memory footprint and I/O
overhead.
**Use Lightweight Stack Tracing**: Replaces with_stack with with_modules
when torch_profiler_with_stack is enabled. In torch_npu, with_stack
introduces heavy latency. with_modules provides equivalent semantic
information with much lower overhead.
**Code Simplification:** Removes redundant parameter configurations in
_ExperimentalConfig by utilizing default values, making the codebase
cleaner and easier to maintain.
**Test setup:**
max length = 50, profiler + stack enabled
**Before optimization:**
Profiler data size: 651 MB
Generate time: 3 seconds
**After optimization:**
Profiler data size: 156 MB (≈76% reduction)
Generate time: <1 second
### Does this PR introduce _any_ user-facing change?
No API changes. Users profiling on Ascend will experience faster
profiling execution and smaller trace files when stack tracing is
enabled.
### How was this patch tested?
Manually verified on Ascend NPU by running vLLM with the profiler
enabled. Confirmed that trace files are generated correctly containing
necessary stack/module info, while showing the reported reduction in
size and time.
- vLLM version: v0.13.0
- vLLM main:
d68209402d
Signed-off-by: mengchengTang <745274877@qq.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.
This time, we performed the operator fusion of MatmulAllReduceAddRMSNorm
and added corresponding ST test cases for regression monitoring.
### Does this PR introduce _any_ user-facing change?
No
### How was this patch tested?
- vLLM version: v0.13.0
- vLLM main:
2c24bc6996
---------
Signed-off-by: cjian <2318164299@qq.com>
### What this PR does / why we need it?
This PR removes `update_default_aclgraph_sizes`. In earlier versions, we
add this function to change default `cudagraph_capture_sizes` because
`_npu_paged_attention` degrades significantly on certain shapes (which
is included in default `cudagraph_capture_sizes` of VLLM). Now since we
use FIA as default attention op (which does not contain such performance
degradation), there is no need to add this default change. Otherwise, it
could cause some conflicts if we set a small `cudagraph_capture_sizes`
that < 20 now.
### Does this PR introduce _any_ user-facing change?
### How was this patch tested?
- vLLM version: v0.14.1
- vLLM main:
d68209402d
---------
Signed-off-by: Angazenn <supperccell@163.com>
This PR fixes the numerical error in moe_load accumulation under ACL
graph mode on NPU: using += for NPU tensors in graph mode does not throw
errors but leads to incorrect values, so we replace it with the in-place
add_() method to ensure accurate calculation.
Signed-off-by: Mercykid-bash <ruanche0218@gmail.com>
- Fixed the computing of final hidden_states when enabling pipeline
parallel and prefill context parallel at the same time. Only in the last
PP rank, hidden_states are required and have right tensor type.
- Fixed the shape of intermediate_tensors in the dummy_run when enabling
pipeline parallel and flashcomm1. The intermediate_tensors should be
divided by tp_size. Otherwise, the moe will raise issues.
- Fixed the shape of self.intermediate_tensors for sufficient slice
space
- vLLM version: release/v0.13.0
- vLLM main:
81786c8774
---------
Signed-off-by: Jingchun Gao <gaojingchun1@huawei.com>
### What this PR does / why we need it?
The static kernel in torch_npu is uninstalled through Python's atexit
mechanism.
However, in vllm-ascend, when inference ends or the service stops, the
worker process is terminated. This way, ending the process does not
trigger the atexit mechanism, causing the static kernel not to be
unloaded.
When using the nougraph_ex backend and enabling the static kernel, we
registered a signal handler to explicitly unload the static kernel.
When there are many static kernels, unloading usually takes some time,
whereas vllm will directly kill the process after sending a terminate
event. Therefore, we choose to handle it by starting a new process.
### Does this PR introduce _any_ user-facing change?
### How was this patch tested?
- vLLM version: v0.13.0
- vLLM main:
d68209402d
---------
Signed-off-by: chencangtao <chencangtao@huawei.com>
Co-authored-by: chencangtao <chencangtao@huawei.com>
### What this PR does / why we need it?
310P support guides updates, as currently has supported in main branch.
---------
Signed-off-by: leo-pony <nengjunma@outlook.com>
### What this PR does / why we need it?
To support elastic scaling when using mooncake connector, we should
support to **configure different tp sizes for different nodes**.
As a result, we transfer the prefill node information, such as tp size,
through **the request's kv_transfer_params**.
The decode nodes **get the prefill tp size** through the request's
kv_transfer_params, instead of getting it from the configuration of the
mooncake connector .
- vLLM version: v0.13.0
- vLLM main:
2f4e6548ef
Signed-off-by: yuxinshan <syx_ctyg@126.com>
Signed-off-by: CalvinXKY <kyxiezju@163.com>
### What this PR does / why we need it?
After removing codepsell a while, we discovered that typo had a problem
correctly recognizing certain misspelled words, so I suggested adding it
back.
- vLLM version: v0.14.1
- vLLM main:
d68209402d
---------
Signed-off-by: wangli <wangli858794774@gmail.com>
### What this PR does / why we need it?
Align with upstream vLLM. This PR will help downstream vLLM-Omni reduce
the cost for maintaining the _prepare_inputs. Besides, it helps
vLLM-Ascend code more readable. In the future, we can follow closer to
vLLM. The `preprocess` logic is same as GPUModelRunner. We don't need to
maintain it anymore.
### Does this PR introduce _any_ user-facing change?
No
### How was this patch tested?
CI.
- vLLM version: v0.14.0
- vLLM main:
d68209402d
---------
Signed-off-by: gcanlin <canlinguosdu@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?
Implement `apply_top_k_top_p` via ascendC to eliminate the constraint of
k [1,1024]. It enables high performance TopKTopP calculation and avoid
D2H synchronization introduced by k validation.
### Does this PR introduce _any_ user-facing change?
No.
### How was this patch tested?
E2E serving with `k=4096` and `p=0.95`
- vLLM version: v0.13.0
- vLLM main:
d68209402d
---------
Signed-off-by: linfeng-yuan <1102311262@qq.com>
Signed-off-by: SlightwindSec <slightwindsec@gmail.com>
Co-authored-by: SlightwindSec <slightwindsec@gmail.com>
### What this PR does / why we need it?
This patch purpose to add the `update_max_model_len` interface.
- vLLM version: v0.14.0
- vLLM main:
d68209402d
---------
Signed-off-by: wangli <wangli858794774@gmail.com>
### What this PR does / why we need it?
In vLLM-Omni, there exists the empty `ModelConfig`. We need to add a
check before accessing the sub-field of model_config.
### Does this PR introduce _any_ user-facing change?
No
### How was this patch tested?
Will checked by CI.
- vLLM version: v0.14.0
- vLLM main:
d68209402d
Signed-off-by: gcanlin <canlinguosdu@gmail.com>
This reverts commit 8966a99710.
It breaks the test
`tests/e2e/singlecard/spec_decode/test_mtp_eagle_correctness.py::test_deepseek_mtp_correctness[True-FULL_DECODE_ONLY-2-wemaster/deepseek_mtp_main_random_bf16]`
- vLLM version: v0.14.0
- vLLM main:
d68209402d
