GitLab

Signed-off-by: ahao-anyscale <ahao@anyscale.com>
Signed-off-by: Aaron Hao <ahao@anyscale.com>
Co-authored-by: SumanthRH <sumanthrh99@gmail.com>

Signed-off-by: mariohong <mariohong128@gmail.com>

Signed-off-by: wang.yuqi <yuqi.wang@daocloud.io>

Signed-off-by: Liran Schour <lirans@il.ibm.com>
Signed-off-by: liranschour <liranschour@users.noreply.github.com>
Co-authored-by: Or Ozeri <or@ozery.com>
Co-authored-by: Nicolò Lucchesi <nicolo.lucchesi@gmail.com>
Co-authored-by: Nicolò Lucchesi <nlucches@redhat.com>

Signed-off-by: Andreas Karatzas <akaratza@amd.com>
Signed-off-by: Matthew Wong <Matthew.Wong2@amd.com>
Co-authored-by: Matthew Wong <Matthew.Wong2@amd.com>

Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Signed-off-by: wang.yuqi <yuqi.wang@daocloud.io>
Co-authored-by: wang.yuqi <yuqi.wang@daocloud.io>

Signed-off-by: Mark McLoughlin <markmc@redhat.com>

Signed-off-by: Andreas Karatzas <akaratza@amd.com>
Signed-off-by: wang.yuqi <yuqi.wang@daocloud.io>
Co-authored-by: wang.yuqi <yuqi.wang@daocloud.io>

[CI][AMD][BugFix] Ensure VLLM_ROCM_USE_AITER is set so test_rocm_aiter_topk.py can run correctly (#33840)
Signed-off-by: Randall Smith <Randall.Smith@amd.com>

Signed-off-by: Nick Hill <nickhill123@gmail.com>

Signed-off-by: Andreas Karatzas <akaratza@amd.com>

Signed-off-by: Luka Govedič <lgovedic@redhat.com>
Signed-off-by: ProExpertProg <luka.govedic@gmail.com>
Signed-off-by: Luka Govedič <ProExpertProg@users.noreply.github.com>

Signed-off-by: Ilya Boytsov <ilyaboytsov1805@gmail.com>
Signed-off-by: Ilya Boytsov <boytsovpanamera@mail.ru>
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
Co-authored-by: wang.yuqi <yuqi.wang@daocloud.io>

Signed-off-by: Nick Hill <nickhill123@gmail.com>

Signed-off-by: Richard Zou <zou3519@gmail.com>

Signed-off-by: simondanielsson <simon.danielsson99@hotmail.com>

Signed-off-by: Kourosh Hakhamaneshi <kourosh@anyscale.com>

Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>

Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>

Fixes a not-yet-reported case where it was possible for blocks to be
freed by an abort before an async transfer completed, resulting
in corrupted KV data.
Signed-off-by: Or Ozeri <oro@il.ibm.com>

Add labeled Prometheus metrics to distinguish where prompt tokens come
from in P/D disaggregated deployments.

In P/D disaggregation, decode instances receive KV cache from prefill instances.
Currently, decode reports inflated prompt throughput because it counts all
prompt tokens as "computed", even though most were transferred.

This PR adds labeled metrics so users can understand actual compute work vs
transferred work:

vllm:prompt_tokens_by_source_total{source="local_compute"}        # Tokens prefilled locally
vllm:prompt_tokens_by_source_total{source="external_kv_transfer"} # Tokens received via KV transfer  
vllm:prompt_tokens_by_source_total{source="local_cache_hit"}      # Tokens from local prefix cache
vllm:prompt_tokens_cached_total                                    # Total cached (local + external, -1 when all 
Signed-off-by: Zhanqiu Hu <zh338@cornell.edu>

Signed-off-by: frankwang28 <frank.wbb@hotmail.com>

Signed-off-by: Rehan Khan <Rehan.Khan7@ibm.com>

Signed-off-by: Andrew Xia <axia@fb.com>
Co-authored-by: Andrew Xia <axia@fb.com>

Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>

Signed-off-by: wang.yuqi <yuqi.wang@daocloud.io>

Signed-off-by: Nick Hill <nickhill123@gmail.com>

Signed-off-by: Patrick von Platen <patrick.v.platen@gmail.com>

Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>

Signed-off-by: Richard Zou <zou3519@gmail.com>

Signed-off-by: zxy <zhou0493@e.ntu.edu.sg>
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Co-authored-by: Isotr0py <mozf@mail2.sysu.edu.cn>

Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>

Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>

Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>

Signed-off-by: carlory <baofa.fan@daocloud.io>
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>

Signed-off-by: Daniel Mescheder <dmesch@amazon.com>
Co-authored-by: Daniel Mescheder <dmesch@amazon.com>

Signed-off-by: Patrick von Platen <patrick.v.platen@gmail.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>

Signed-off-by: vasiliy <vasiliy@fb.com>

  Reduce the kernel overhead when num of active loras is smaller than max loras. Multiple cuda graphs are captured for each num of active-loras. (#32005)
Signed-off-by: Yu Gong <yu3.gong@gmail.com>