2025-02-05 10:53:12 +08:00
|
|
|
[mypy]
|
|
|
|
|
; warn_return_any = True
|
|
|
|
|
warn_unused_configs = True
|
|
|
|
|
|
|
|
|
|
; Suppress all missing import errors from torch_npu for mypy.
|
|
|
|
|
[mypy-torch_npu.*]
|
|
|
|
|
ignore_missing_imports = True
|
|
|
|
|
|
Support multistream of shared experts in FusedMoE (#997)
Contains on #1111 for completeness.
<!-- 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?
Implement multi-stream parallelism for MoE layers with shared experts,
where computation of shared experts will be overlapped with expert token
dispatch and combine. Also, when multi-stream is enabled, weights of
shared experts will be force to replicate across all cards, regardless
of any tensor parallelism configurations, to avoid AllReduce operations.
With the expected overlaping being:
```
| shared gate_up | shared act | | shared down |
| dispatch | routed gate_up, act, down | combine |
```
<!--
- 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?
Tested on 1x16 910 node, with tailored 2 layer DSKv2.
<!--
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: sdmyzlp <lrwei2@petalmail.com>
2025-06-11 09:18:38 +08:00
|
|
|
[mypy-torchair.*]
|
|
|
|
|
ignore_missing_imports = True
|
|
|
|
|
|
2025-02-05 10:53:12 +08:00
|
|
|
[mypy-transformers.*]
|
|
|
|
|
ignore_missing_imports = True
|
|
|
|
|
|
2025-04-17 14:59:56 +08:00
|
|
|
[mypy-lm_eval.*]
|
2025-11-24 21:58:31 +08:00
|
|
|
ignore_missing_imports = True
|
|
|
|
|
|
[Quantization] Support compressed tensors w8a8 static and w8a8 dynamic weight (#4036)
### 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. Add AscendCompressedTensorsConfig to replace CompressedTensorsConfig
in vllm.
2. Support CompressedTensorsW8A8 static weight.
- weight: per-channel, int8, symmetric; activation: per-tensor, int8,
symmetric.
4. Support CompressedTensorsW8A8Dynamic weight.
- weight: per-channel, int8, symmetric; activation: per-token, int8,
symmetric, dynamic.
5. Modify the override_quantization_method in AscendQuantConfig.
Co-authored-by: taoqun110 taoqun@huawei.com
Co-authored-by: chenxi-hh chen464822955@163.com
- vLLM version: v0.11.2
---------
Signed-off-by: LHXuuu <scut_xlh@163.com>
Signed-off-by: chenxi-hh <chen464822955@163.com>
Signed-off-by: chenxi-hh <32731611+chenxi-hh@users.noreply.github.com>
Co-authored-by: chenxi-hh <chen464822955@163.com>
Co-authored-by: chenxi-hh <32731611+chenxi-hh@users.noreply.github.com>
2025-11-28 14:09:39 +08:00
|
|
|
[mypy-compressed_tensors.*]
|
|
|
|
|
ignore_missing_imports = True
|
|
|
|
|
|
|
|
|
|
[mypy-datasets.*]
|
|
|
|
|
ignore_missing_imports = True
|
|
|
|
|
|
|
|
|
|
[mypy-llmcompressor.*]
|
|
|
|
|
ignore_missing_imports = True
|
|
|
|
|
|
2025-11-24 21:58:31 +08:00
|
|
|
[mypy-msprobe.*]
|
|
|
|
|
ignore_missing_imports = True
|
2025-12-08 08:27:46 +08:00
|
|
|
|
|
|
|
|
[mypy-xlite.*]
|
[Core][Worker] Add UCMConnector for KV Cache Offloading (#4411)
### What this PR does / why we need it?
This PR introduces the initial integration of **UCM (Unified Cache
Management)** into the vllm-ascend distributed KV-cache system.
Specifically, it adds:
- A new `UCMConnector` implementation under the distributed KV-transfer
framework.
- Support for offloading KV-cache blocks to external UCM backends (DRAM
/ NFS / Localdisk), depending on UCM configuration).
- Integration with vLLM V1 KV connector interface, including metadata
handling and role registration.
**Why it is needed:**
- UCM provides a unified, high-performance storage layer for KV-cache
externalization.
- This enables vllm-ascend to support out-of-core KV-cache workloads,
improve memory efficiency, and leverage hardware-accelerated storage
paths (RDMA / NFS / hybrid modes).
- This connector is a required component to allow future work on
multi-node inference + UCM-based scaling.
---
### Does this PR introduce _any_ user-facing change?
Yes, but limited:
- A new `kv_connector=UCMConnector` option becomes available through the
configuration interface.
- When selected, vllm-ascend workers may initialize UCM and offload
KV-cache blocks externally.
- No default behaviors are changed. Users must explicitly enable this
connector.
This PR does **not** modify:
- existing APIs,
- default execution paths,
- model runner behavior,
- user workflow unless `UCMConnector` is configured.
---
### How was this patch tested?
---
### Prefix Caching Benchmark
We provide preliminary measurements for TTFT (ms) under VLLM benchmark.
Tests run on 2 * Ascend 910B3, vllm-ascend 0.11.0, Tensor Parallel size
2, with UCM (Localdisk) enabled.
- vLLM version: v0.12.0
- vLLM main:
https://github.com/vllm-project/vllm/commit/ad32e3e19ccf0526cb6744a5fed09a138a5fb2f9
Signed-off-by: UnifiedCacheManager <unifiedcachem@163.com>
2025-12-16 10:53:30 +08:00
|
|
|
ignore_missing_imports = True
|
|
|
|
|
|
|
|
|
|
[mypy-ucm.*]
|
2025-12-08 08:27:46 +08:00
|
|
|
ignore_missing_imports = True
|