[compile] Add FlashInfer FP8 async TP fusion and preserve allreduce fusion ordering #27893 (#39505)

Signed-off-by: baonudesifeizhai <baonudesifeizhai@gmail.com>
Signed-off-by: baonudesifeizhai <85092850+baonudesifeizhai@users.noreply.github.com>
Signed-off-by: roG0d <baonudesifeizhai@gmail.com>
This commit is contained in:
baonudesifeizhai
2026-05-01 05:08:34 +00:00
committed by GitHub
parent 947138b6c2
commit c3868bbbe4
6 changed files with 397 additions and 30 deletions
+6
View File
@@ -97,6 +97,12 @@ def run_e2e_fusion_test(monkeypatch, caplog_mp_spawn):
f"attention backend '{attn_backend.backend.name}'"
)
if attn_backend.backend.name == "FLASHINFER":
from vllm.utils.flashinfer import supports_trtllm_attention
if not supports_trtllm_attention():
matches = matches._replace(attn_quant_fusion=0)
# TODO: remove this after finishing migration from envs to model kwargs
if model_name == "openai/gpt-oss-20b":
from .common import is_blackwell