xc-llm-ascend

Files

Ruri aff5189c87 [main] Fuse GroupedMatmul, Swiglu and DynamicQuant in W8A8_DYNAMIC quantized MoE layers (#2275 )

### What this PR does / why we need it?

Fuse `GroupedMatmul`, `Swiglu` and `DynamicQuant` into one fusion
operation `GroupedMatmulSwigluQuant`.

1. extract common functions in `w4a8_dynamic.py` and `w8a8_dynamic.py`
2. if in supported occasion, use fusion operation
`npu_grouped_matmul_swiglu_quant`

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

### How was this patch tested?

Tested on W8A8 quantized Qwen3-235B-A22B model with `bs=16`

1. `tp=8`, `dp=1`, `moe_tp=8`, `moe_ep=1`, TPOP increased 21.54%, Output
Token Throughput increased 27.35%
<img width="3443" height="211" alt="image"
src="https://github.com/user-attachments/assets/a1a9c14d-2310-41be-9a03-36125dabae6e"
/>

3. `tp=8`, `dp=1`, `moe_tp=1`, `moe_ep=8`, TPOP increased 17.38%, Output
Token Throughput increased 6.86%
<img width="3443" height="211" alt="image"
src="https://github.com/user-attachments/assets/1ce92e92-720d-40c0-8b4d-c493e5cb10a6"
/>


- vLLM version: v0.10.1.1
- vLLM main:
6997a25ac6

---------

Signed-off-by: Ruri <33858552+zhoux77899@users.noreply.github.com>
Signed-off-by: zhoux77899 <zhouxiang100@huawei.com>

2025-09-04 11:37:32 +08:00

attention

[BugFix][MLA] Fix attn_mask bug for ring mla (#2704 )

2025-09-04 10:22:46 +08:00

compilation

[Bugfix] Fix aclgraph not enabled by default (#2590 )

2025-08-28 14:08:31 +08:00

core

[Bugfix][APC] Fix accuracy issue on prefix caching with AscendScheduler (#2714 )

2025-09-04 08:22:46 +08:00

device_allocator

[Misc]Clean up useless import from vllm (#2049 )