XiaoxinWang e38ef2c434 support FULL graph mode for GQA (#3970) ...

### What this PR does / why we need it?
The current library only supports the FullDecodeOnly graph mode, which
enables full graph execution during the decode. This PR extends support
to allow full graph execution in both the prefill and decode, referred
to as FULL graph mode.

- vLLM version: v0.11.0
- vLLM main:
2918c1b49c

Signed-off-by: wangxiaoxin-sherie <wangxiaoxin7@huawei.com>
Co-authored-by: wangxiaoxin-sherie <wangxiaoxin7@huawei.com>

2025-11-17 10:50:35 +08:00

..

test_v1_mtp_correctness.py

support FULL graph mode for GQA (#3970)

2025-11-17 10:50:35 +08:00

test_v1_mtp_torchair_correctness.py

[Feat]Make full graph mode compalible with MTP (#3276)

2025-10-17 20:19:56 +08:00

test_v1_spec_decode.py

[main][Bugfix] Fix ngram precision issue and open e2e ngram test (#4090)

2025-11-11 09:06:24 +08:00