[Bugfix][MRV2] Fix speculative warmup deadlock with pipeline parallelism (#62129)
Signed-off-by: chenjr97 <chenjr97@mail2.sysu.edu.cn> Co-authored-by: Nick Hill <nickhill123@gmail.com> Co-authored-by: vllm-agent <claw@inferact.ai>
This commit is contained in:
co-authored by
Nick Hill
vllm-agent
parent
da9134bc89
commit
7c9042c05a
@@ -238,7 +238,8 @@ def warmup_kernels(
|
||||
rejection_sampler.enable_adaptive_verification = False
|
||||
try:
|
||||
_warmup_kernels(model_runner, worker_execute_model, worker_sample_tokens)
|
||||
if rejection_sampler is not None:
|
||||
# All PP ranks must run the same forwards to match sends and receives.
|
||||
if model_runner.speculative_config is not None:
|
||||
# Greedy batches skip logits processing, so rejection kernels
|
||||
# also see model-dtype logits instead of FP32.
|
||||
_warmup_kernels(
|
||||
|
||||
Reference in New Issue
Block a user