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

..

attention

[Refactor]refactor 310p attention impl and add ut (#6579)

2026-02-07 09:26:26 +08:00

fused_moe

[Refact]Refact MLA/SFA weight prefetch to consist with moe weight prefetch (#6629)

2026-02-10 14:14:37 +08:00

ops

[Refactor]refactor 310p ops and add ut (#6591)

2026-02-07 09:25:17 +08:00

quantization

[Refactor]refactor 310p ops and add ut (#6591)

2026-02-07 09:25:17 +08:00

__init__.py

[Feature]: Support 310P device run qwen2.5/3 dense and qwen2.5vl models (#5776)

2026-01-17 11:49:18 +08:00

model_runner_310p.py

[Bugfix]Fix the compatibility issue of may_reinitialize_input_batch (#6290)

2026-02-02 19:16:26 +08:00

worker_310p.py

[Refactor]310p_e2e test case update (#6539)

2026-02-07 09:28:37 +08:00