xc-llm-ascend

Files

CaranLic 168ad600b5 [main] add pd transfer for ascend scheduler (#2753 )

### What this PR does / why we need it?
For offline scenarios, adjust the scheduling process to prioritize the
prefill phase of all requests, then process the decode phase of all
requests.

### How was this patch tested?

```
max_num_seqs=24,
additional_config={
    "ascend_scheduler_config":{
        "enabled": True,
        "enable_pd_transfer": True,
        "decode_max_num_seqs": 24,
        "enable_chunked_prefill": False
    }
},
```
| input | output | num prompts | max_num_seqs | dp | tp | scheduler |
tps |
| ------ | ------ | ---------- | ---------------- | ---- | ---- |
---------------- | --------------- |
| dapo-math-17K | 2K | 384 | 24 | 2 | 1 | v1 | 234.06 |
| dapo-math-17K | 2K | 384 | 24 | 2 | 1 | pd transfer | 239.59(+2.4%) |
| dapo-math-17K| 2K | 384 | 24 | 4 | 1 | v1 | 222.85 |
| dapo-math-17K| 2K | 384 | 24 | 4 | 1 | pd transfer | 225.81(+1.3%) |


- vLLM version: v0.10.1.1
- vLLM main:
6fb2788163

---------

Signed-off-by: CaranLic <740821011@qq.com>

2025-09-10 08:46:39 +08:00

attention

[fix] prefill unsupport sliding window attention (#2758 )

2025-09-07 10:34:38 +08:00

core

[main] add pd transfer for ascend scheduler (#2753 )

2025-09-10 08:46:39 +08:00

device_allocator

add ut for device allocator/camem and mutistream/layers (#2037 )

2025-07-31 19:17:27 +08:00

distributed

[feat]: oproj tensor parallelism in pure DP and graph-mode scenarios. (#2167 )