EngineX-Hygon/sglang
5
0
Fork 0
Code Issues Pull Requests Actions 7 Projects Releases Wiki Activity

[PD] Respect sampling_params.max_new_tokens when PD disaggregation is activated (#7598)

Browse Source 
Signed-off-by: Shangming Cai <caishangming@linux.alibaba.com>
This commit is contained in:
Shangming Cai
2025-06-28 13:22:01 +08:00
committed by GitHub
parent 49538d111b
commit eb429b88a4
1 changed files with 13 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

14
python/sglang/srt/disaggregation/decode.py
View File

@@ -604,9 +604,21 @@ class DecodeTransferQueue:
: decode_req.req.top_logprobs_num : decode_req.req.top_logprobs_num
].tolist() ].tolist()
) )
if hasattr(decode_req.kv_receiver, "clear"): if hasattr(decode_req.kv_receiver, "clear"):
decode_req.kv_receiver.clear() decode_req.kv_receiver.clear()
transferred_reqs.append(decode_req.req)
# special handling for sampling_params.max_new_tokens == 1
if decode_req.req.sampling_params.max_new_tokens == 1:
# finish immediately
decode_req.req.check_finished()
self.scheduler.stream_output(
[decode_req.req], decode_req.req.return_logprob
)
self.tree_cache.cache_finished_req(decode_req.req)
else:
transferred_reqs.append(decode_req.req)
indices_to_remove.add(i) indices_to_remove.add(i)
elif poll in [ elif poll in [
KVPoll.Bootstrapping, KVPoll.Bootstrapping,