[Core][V1] Support trace_decode_token_ids for deterministic decode replay (#46701)
Signed-off-by: ianzxliu <ianzxliu@tencent.com> Signed-off-by: aoshen02 <aoshen@inferact.ai> Signed-off-by: Zhixia Liu <liuzhixia.nju@gmail.com> Co-authored-by: ianzxliu <ianzxliu@tencent.com> Co-authored-by: Claude <noreply@anthropic.com> Co-authored-by: aoshen02 <aoshen@inferact.ai> Co-authored-by: Codex <noreply@openai.com> Co-authored-by: Nick Hill <nickhill123@gmail.com>
This commit is contained in:
co-authored by
ianzxliu
Claude
aoshen02
Codex
Nick Hill
parent
754e1c3de4
commit
a1c5b1fd9f
@@ -408,6 +408,7 @@ class GPUModelRunner(LoRAModelRunnerMixin):
|
||||
logprobs_mode=self.model_config.logprobs_mode,
|
||||
num_speculative_tokens=self.decode_query_len,
|
||||
use_fp64_gumbel=self.model_config.use_fp64_gumbel,
|
||||
enable_trace_replay=self.model_config.enable_trace_replay,
|
||||
reasoning_config=self.vllm_config.reasoning_config,
|
||||
return_sampling_mask=self.model_config.return_sampling_mask,
|
||||
)
|
||||
|
||||
Reference in New Issue
Block a user