EngineX/xc-llm-ascend
3
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity
2,516 Commits 3 Branches 0 Tags
1c0ecf806ad871b05875c835fe3ae22d6e60ead7
Commit Graph

9 Commits

Author SHA1 Message Date
tanhaoan333
15f6564976 [Model]Add Qwen3-Omni quantization Ascend NPU adaptation and optimization (#6828) 
### What this PR does / why we need it?
This pull request is for quantization adaptation of Qwen3Omni, and it
achieves operator-level optimization and AUT (Auto-Quantization Tuning)
component optimization through patch-based modifications.
### Does this PR introduce _any_ user-facing change?

### How was this patch tested?

- vLLM version: v0.15.0
- vLLM main:
83b47f67b1

---------

Signed-off-by: tanhaoan333 <tanhaoan@huawei.com>
 2026-03-03 00:07:23 +08:00
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:
15d76f74e2

---------

Signed-off-by: linfeng-yuan <1102311262@qq.com>
 2026-03-02 18:17:01 +08:00
Eric-dot
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:
13397841ab

---------

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
Cao Yi
53b494b1e4 [main][Quant] Remove unused rotation functions and parameters from W4A4 LAOS quantization (#6648) 
## Summary
- Remove unused `set_rotation_config` and `apply_rotation` methods from
`AscendW4A4LaosDynamicLinearMethod`
- Remove unused `rotation_type` field and associated conditional
quantization parameters (`heads_rotation`, `kronecker_rotation_n`,
`kronecker_rotation_m`)

These rotation-related functions and parameters are never called in the
current W4A4 LAOS dynamic quantization workflow.

- vLLM version: v0.15.0
- vLLM main:
d7e17aaacd

Signed-off-by: SlightwindSec <slightwindsec@gmail.com>
 2026-02-11 16:38:45 +08:00
Nengjun Ma
66b60c9440 [Refact]Refact MLA/SFA weight prefetch to consist with moe weight prefetch (#6629) 
### What this PR does / why we need it?
1. [Refact] Refact MLA/SFA weight prefetch to consist with moe weight
prefetch
2. Remove duplicated o_proj weight prefetch in forward for MLA/SFA

### Does this PR introduce _any_ user-facing change?
NA

### How was this patch tested?

1) Performance result:
Perf test data:
*) MLA:

| | 1st test | 2nd test | Output Token Throughput(Avg) | Performance
improvement percentage |
| --- | --- | --- | --- | --- |
| o_proj duplicate prefetch | 11.9669 token/s | 12.0287 token/s |
11.9978 |
| o_proj no duplicate prefetch | 12.5594 token/s | 12.6216 token/s |
12.5905 | 4.94%| |

single layer performace improve: 5%~8%

*) SFA:

| | 1st test | 2nd test | Output Token Throughput(Avg) | Performance
improvement percentage |
| --- | --- | --- | --- | --- |
| o_proj duplicate prefetch | 13.0523 token/s | 13.1084 token/s |
13.08035 | |
| o_proj no duplicate prefetch | 13.9844 token/s | 14.1678 token/s |
14.0761 | 7.6% |

- vLLM version: v0.15.0
- vLLM main:
d7e17aaacd

---------

Signed-off-by: leo-pony <nengjunma@outlook.com>
 2026-02-10 14:14:37 +08:00
SILONG ZENG
99aedaff63 [Lint]Style: Convert vllm-ascend/ to ruff format(Batch #7) (#6023) 
### What this PR does / why we need it?
**Scope of Changes**:
| File Path |
| :--- |
|` vllm_ascend/quantization/compressed_tensors/compressed_tensors.py`|
|` vllm_ascend/quantization/quant_config.py`|
|` vllm_ascend/quantization/utils.py`|
|` vllm_ascend/quantization/w4a16.py`|
|` vllm_ascend/quantization/w4a4_flatquant_dynamic.py`|
|` vllm_ascend/quantization/w4a8_dynamic.py`|
|` vllm_ascend/quantization/w8a16.py`|
|` vllm_ascend/quantization/w8a8.py`|
|` vllm_ascend/quantization/w8a8_dynamic.py`|
|` vllm_ascend/quantization/w8a8_pdmix.py`|
|` vllm_ascend/quantization/w8a8mxfp8.py`|
|` vllm_ascend/sample/rejection_sampler.py`|
|` vllm_ascend/sample/sampler.py`|
|` vllm_ascend/worker/block_table.py`|

### Does this PR introduce _any_ user-facing change?

### How was this patch tested?

- vLLM version: v0.13.0
- vLLM main:
2c24bc6996

Signed-off-by: MrZ20 <2609716663@qq.com>
 2026-02-06 14:56:53 +08:00
Shaoxu Cheng
39e77fb9e4 [Feat.]: support 310p w8a8 (#6454) 
### What this PR does / why we need it?
Introduced 310P W8A8 Quantization Support: New modules and methods have
been added to enable W8A8 static quantization specifically for the
Ascend 310P platform.
Platform-Specific Quantization Configuration Loading: The system now
dynamically loads the appropriate quantization configurations
(AscendCompressedTensorsConfig, AscendModelSlimConfig) based on whether
the current hardware is an Ascend 310P device.
Implemented AscendW8A8LinearMethod310P: A dedicated linear quantization
method for 310P is provided, handling the specifics of weight and
activation quantization, including input parameter broadcasting and
weight data manipulation.
Extended AscendModelSlimConfig for 310P: A specialized configuration
class for 310P integrates the new W8A8 linear method for both standard
linear layers and vocabulary parallel embeddings, ensuring proper
quantization application.

- vLLM version: v0.14.1
- vLLM main:
dc917cceb8

---------

Signed-off-by: Tflowers-0129 <2906339855@qq.com>
Signed-off-by: Shaoxu Cheng <2906339855@qq.com>
 2026-02-03 14:13:06 +08:00
LHXuuu
45a573cff1 [Quantization][Feature] Support compressed tensors moe w4a8 dynamic weight (#5889) 
### 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>
 2026-02-02 16:39:32 +08:00
Cao Yi
a69ef10c3a [Refactor] Quantization Module Refactor (#5738) 
### Summary

This PR refactors the `vllm_ascend/quantization` module to improve code
organization, maintainability, and extensibility. The refactoring
introduces a clear separation of concerns with a registry-based scheme
discovery pattern, abstract base classes for quantization schemes, and
dedicated wrapper classes.

### Key Changes

#### 1. **Modular Directory Structure**

| Before | After |
|--------|-------|
| Flat file structure with mixed responsibilities | Organized into
`methods/` subpackage for schemes |
| Single `quant_config.py` (600+ lines) | Separate config files:
`modelslim_config.py`, `compressed_tensors_config.py` |
| `utils.py` with scheme lookup logic | `methods/registry.py` with
decorator-based registration |

#### 2. **Registry-Based Scheme Discovery**

Replaced hardcoded `ASCEND_QUANTIZATION_METHOD_MAP` dictionary with a
decorator-based registry pattern:

```python
# Before: Manual dictionary mapping
ASCEND_QUANTIZATION_METHOD_MAP = {
    "W8A8_DYNAMIC": {"linear": AscendW8A8DynamicLinearMethod, ...},
    ...
}

# After: Decorator-based registration
@register_scheme("W8A8_DYNAMIC", "linear")
class AscendW8A8DynamicLinearMethod(AscendLinearScheme):
    ...
```

#### 3. **Abstract Base Classes**

Introduced three abstract base classes in `methods/base.py`:
- `AscendLinearScheme` - Base for linear layer quantization
- `AscendMoEScheme` - Base for MoE layer quantization  
- `AscendAttentionScheme` - Base for attention layer quantization

#### 4. **Separated Config and Wrapper Classes**

- **Config classes** (`AscendModelSlimConfig`,
`AscendCompressedTensorsConfig`): Handle config parsing and scheme
selection
- **Wrapper classes** (`AscendLinearMethod`, `AscendFusedMoEMethod`,
etc.): Implement vLLM interfaces and delegate to schemes

#### 5. **Cleaner Public API**

```python
# New clean module interface
from vllm_ascend.quantization import (
    AscendModelSlimConfig,
    AscendCompressedTensorsConfig,
)
from vllm_ascend.quantization.methods import get_scheme_class
```

### Architecture Diagram

```mermaid
classDiagram
    direction TB
    
    class QuantizationConfig {
        <<vLLM Interface>>
        +get_quant_method()
    }
    
    class AscendModelSlimConfig {
        +quant_description
        +get_quant_method()
        -create_scheme_for_layer()
    }
    
    class AscendCompressedTensorsConfig {
        +target_scheme_map
        +get_quant_method()
        -_get_scheme_from_parts()
    }
    
    class AscendLinearMethod {
        <<Wrapper>>
        +quant_method: AscendLinearScheme
        +create_weights()
        +apply()
    }
    
    class AscendFusedMoEMethod {
        <<Wrapper>>
        +quant_method: AscendMoEScheme
        +create_weights()
        +apply()
    }
    
    class AscendLinearScheme {
        <<Abstract>>
        +get_weight()*
        +apply()*
        +get_pertensor_param()
        +get_perchannel_param()
    }
    
    class AscendMoEScheme {
        <<Abstract>>
        +get_weight()*
        +get_dynamic_quant_param()*
        +apply()*
    }
    
    class W8A8DynamicLinear {
        +get_weight()
        +apply()
    }
    
    class W8A8DynamicMoE {
        +get_weight()
        +apply()
    }
    
    QuantizationConfig <|-- AscendModelSlimConfig
    QuantizationConfig <|-- AscendCompressedTensorsConfig
    
    AscendModelSlimConfig ..> AscendLinearMethod : creates
    AscendModelSlimConfig ..> AscendFusedMoEMethod : creates
    AscendCompressedTensorsConfig ..> AscendLinearMethod : creates
    AscendCompressedTensorsConfig ..> AscendFusedMoEMethod : creates
    
    AscendLinearMethod o-- AscendLinearScheme : delegates to
    AscendFusedMoEMethod o-- AscendMoEScheme : delegates to
    
    AscendLinearScheme <|-- W8A8DynamicLinear
    AscendMoEScheme <|-- W8A8DynamicMoE
```

### Scheme Registration Flow

```mermaid
sequenceDiagram
    participant Module as Scheme Module
    participant Registry as _SCHEME_REGISTRY
    participant Config as QuantConfig
    participant Wrapper as Wrapper Class
    
    Note over Module: At import time
    Module->>Registry: @register_scheme("W8A8_DYNAMIC", "linear")
    Registry->>Registry: Store (quant_type, layer_type) -> Class
    
    Note over Config: At runtime
    Config->>Config: Determine quant_type from description
    Config->>Registry: get_scheme_class(quant_type, layer_type)
    Registry-->>Config: Return scheme class
    Config->>Config: scheme = scheme_cls()
    Config->>Wrapper: Create wrapper with scheme
    Wrapper-->>Config: Return wrapper instance
```

### File Changes Summary

| Original Files | Refactored Files |
|----------------|------------------|
| `__init__.py` (empty) | `__init__.py` (exports public API) |
| `quant_config.py` | `modelslim_config.py` + `wrappers.py` |
| `compressed_tensors/` | `compressed_tensors_config.py` |
| `utils.py` | `methods/registry.py` |
| `w8a8_dynamic.py` | `methods/w8a8_dynamic.py` |
| `w8a8.py` | `methods/w8a8_static.py` |
| `w4a4_flatquant_dynamic.py` | `methods/w4a4_flatquant.py` |
| ... | `methods/base.py` (new) |

### Benefits

1. **Extensibility**: Adding new quantization schemes only requires
implementing the base class and adding `@register_scheme` decorator
2. **Maintainability**: Clear separation between config parsing, wrapper
logic, and scheme implementation
3. **Testability**: Abstract base classes enable easier unit testing and
mocking
4. **Discoverability**: Registry pattern makes it easy to list all
supported schemes
5. **Reduced Coupling**: Config classes no longer need to know about all
scheme implementations

___

- vLLM version: v0.13.0
- vLLM main:
2f4e6548ef

---------

Signed-off-by: SlightwindSec <slightwindsec@gmail.com>
 2026-01-23 14:13:47 +08:00