EngineX/xc-llm-ascend
3
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity
Files
aa0143e55dfce8064fa6449f8453ef0ae13592d6
xc-llm-ascend/vllm_ascend/worker/v2
History
shiyuan680 3b6b3c4214 [MODELRUNNERV2]fix penality ops (#7013) 
### What this PR does / why we need it?
fix penality ops for new version, and achieved a 10% performance
improvement

### How was this patch tested?
pytest
‎tests/e2e/nightly/single_node/ops/singlecard_ops/triton/test_penality.py
- vLLM version: v0.16.0
- vLLM main:
15d76f74e2

Signed-off-by: shiyuan680 <917935075@qq.com>
2026-03-11 17:13:34 +08:00
..
sample
[MODELRUNNERV2]fix penality ops (#7013)
2026-03-11 17:13:34 +08:00
spec_decode
[Feature] adapt to uva buffer and main2main (#6657)
2026-02-12 10:36:31 +08:00
__init__.py
implement model runner v2 basic framework (#5051)
2025-12-18 15:51:54 +08:00
aclgraph_utils.py
[Feature] adapt to uva buffer and main2main (#6657)
2026-02-12 10:36:31 +08:00
attn_utils.py
[Feature] adapt to uva buffer and main2main (#6657)
2026-02-12 10:36:31 +08:00
input_batch.py
[Feature] adapt to uva buffer and main2main (#6657)
2026-02-12 10:36:31 +08:00
model_runner.py
[Feature] adapt to uva buffer and main2main (#6657)
2026-02-12 10:36:31 +08:00
README.md
[Feature] adapt to uva buffer and main2main (#6657)
2026-02-12 10:36:31 +08:00
states.py
[Feature] adapt to uva buffer and main2main (#6657)
2026-02-12 10:36:31 +08:00
utils.py
[Feature] support eager mode in model runner v2 (#5210)
2025-12-29 15:28:34 +08:00

README.md

[Experimental] Model Runner V2

This directory contains the new model runner which is under active development.

please see Model Runner V2 to get specific plans.

supported vllm version: main@1339784