linfeng-yuan
68d8d20ca2
[misc] move mxfp_compat into device to decouple from quantization init chain ( #6918 )
...
### What this PR does / why we need it?
`mxfp_compat` only provides dtype/symbol compatibility helpers for
different `torch_npu` versions, but it was placed under
`vllm_ascend.quantization`. Importing it from device/ops paths could
trigger `quantization/__init__.py` and pull in heavy quantization method
dependencies, increasing startup coupling and causing import-cycle risk
(especially on 310P paths).
### Does this PR introduce _any_ user-facing change?
No functional behavior change intended.
### How was this patch tested?
CI passed.
- vLLM version: v0.16.0
- vLLM main:
https://github.com/vllm-project/vllm/commit/15d76f74e2fdb12a95ea00f0ca283acf6219a2b7
---------
Signed-off-by: linfeng-yuan <1102311262@qq.com >
2026-03-02 18:17:01 +08:00
3c66a970f2
add mxfp8 moe quantization ( #6670 )
...
### What this PR does / why we need it?
support mxfp8 quantization (Qwen MOE )
Using adaptor to make the hardware-specific behavior clearer and more
maintainable
### How was this patch tested?
- vLLM version: v0.15.0
- vLLM main:
https://github.com/vllm-project/vllm/commit/13397841ab469cecf1ed425c3f52a9ffc38139b5
---------
Signed-off-by: fangrongcan <17343701736@163.com >
Signed-off-by: wangyao-i <iwangyao@outlook.com >
Signed-off-by: linfeng-yuan <1102311262@qq.com >
Signed-off-by: Eric-dot <60131170+Eric-dot@users.noreply.github.com >
Co-authored-by: fangrongcan <f00876277@china.huawei.com >
Co-authored-by: wangyao-i <iwangyao@outlook.com >
Co-authored-by: linfeng-yuan <1102311262@qq.com >
2026-03-02 11:04:06 +08:00
SILONG ZENG
329961b375
[Lint]Style: Convert vllm-ascend/ to ruff format(Batch #2 ) ( #5977 )
...
### What this PR does / why we need it?
**Scope of Changes**:
| File Path |
| :--- |
| `vllm_ascend/attention/attention_mask.py` |
| `vllm_ascend/attention/attention_v1.py` |
| `vllm_ascend/attention/context_parallel/attention_cp.py` |
| `vllm_ascend/attention/context_parallel/common_cp.py` |
| `vllm_ascend/attention/context_parallel/mla_cp.py` |
| `vllm_ascend/attention/utils.py` |
| `vllm_ascend/batch_invariant.py` |
| `vllm_ascend/device/device_op.py` |
| `vllm_ascend/device_allocator/camem.py` |
| `vllm_ascend/envs.py` |
- vLLM version: v0.13.0
- vLLM main:
https://github.com/vllm-project/vllm/commit/2c24bc6996cb165fce92f780b388a5e39b3f4060
---------
Signed-off-by: MrZ20 <2609716663@qq.com >
2026-01-19 08:59:46 +08:00
weijinqian0 and weijinqian_v1
1ccb9acd9a
[Refactor] Provide a framework to accommodate operators for different hardware devices ( #5735 )
...
come from: https://github.com/vllm-project/vllm-ascend/issues/5463
Reason:
During the iteration process of the hardware version, there may be a
large number of iterations for the operators, which can lead to
short-term compatibility differences. Therefore, an intermediate
adaptation layer is provided to accommodate the short-term differences
in operators.
- vLLM version: v0.13.0
- vLLM main:
https://github.com/vllm-project/vllm/commit/2f4e6548efec402b913ffddc8726230d9311948d
---------
Signed-off-by: weijinqian_v1 <weijinqian@huawei.com >
Signed-off-by: weijinqian0 <1184188277@qq.com >
Co-authored-by: weijinqian_v1 <weijinqian@huawei.com >
2026-01-13 09:53:26 +08:00