GitLab

Signed-off-by: Or Ozeri <oro@il.ibm.com>

Signed-off-by: czhu-cohere <conway.zhu@cohere.com>

Signed-off-by: gnovack <gnovack@amazon.com>

Signed-off-by: Yanan Cao <gmagogsfm@gmail.com>

Signed-off-by: yewentao256 <zhyanwentao@126.com>

Signed-off-by: Ziliang Peng <ziliang@character.ai>

Signed-off-by: Ming Yang <minos.future@gmail.com>

Signed-off-by: charlifu <charlifu@amd.com>
Signed-off-by: Charlie Fu <Charlie.Fu@amd.com>

Signed-off-by: Roi Koren <roik@nvidia.com>

Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>

Signed-off-by: Laith Sakka <lsakka@meta.com>

Signed-off-by: Daniel Campora <961215+dcampora@users.noreply.github.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>

[Frontend] Binary embedding response does not return metadata by setting encoding_format to bytes_only. (#30249)
Signed-off-by: wang.yuqi <yuqi.wang@daocloud.io>
Signed-off-by: wang.yuqi <noooop@126.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>

[Model][7/N] Improve all pooling task | Deprecation as_reward_model. Extract hidden states prefer using new multi-vector retrieval API (#26686)
Signed-off-by: wang.yuqi <yuqi.wang@daocloud.io>

Signed-off-by: Daniel Salib <danielsalib@meta.com>

Signed-off-by: ElizaWszola <ewszola@redhat.com>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
Co-authored-by: yewentao256 <zhyanwentao@126.com>

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

Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>

Signed-off-by: Jinzhen Lin <jinzhen.ljz@antgroup.com>
Co-authored-by: Jee Jee Li <pandaleefree@gmail.com>

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

Signed-off-by: yewentao256 <zhyanwentao@126.com>

Signed-off-by: Jeremy Teboul <jeremyteboul@fb.com>
Co-authored-by: Jeremy Teboul <jeremyteboul@fb.com>

Signed-off-by: Yanan Cao <gmagogsfm@gmail.com>

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

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

Signed-off-by: Viacheslav Barinov <viacheslav.teh@gmail.com>

Signed-off-by: piood <2477084691@qq.com>

[CI/Build][AMD] Use ROCM_ATTN instead of FLASH_ATTN test for test_register_kv_caches for ROCm and update test for TRITON_ATTN (#29985)
Signed-off-by: Randall Smith <ransmith@amd.com>
Co-authored-by: Randall Smith <ransmith@amd.com>
Co-authored-by: TJian <tunjian.tan@embeddedllm.com>

[CI/Build][AMD] Skip marlin, machete, and hadacore tests since these require _C functions not defined for ROCm (#30109)
Signed-off-by: Randall Smith <ransmith@amd.com>
Co-authored-by: Randall Smith <ransmith@amd.com>

Signed-off-by: Samuel Shen <slshen@uchicago.edu>
Co-authored-by: Samuel Shen <slshen@uchicago.edu>

Signed-off-by: Debolina Roy <debroy@redhat.com>

Signed-off-by: Divakar Verma <divakar.verma@amd.com>

Signed-off-by: NickLucche <nlucches@redhat.com>

Signed-off-by: Russell Bryant <rbryant@redhat.com>

Signed-off-by: Luka Govedič <lgovedic@redhat.com>
Signed-off-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
Signed-off-by: ilmarkov <markovilya197@gmail.com>
Signed-off-by: Luka Govedič <luka.govedic@gmail.com>
Signed-off-by: ProExpertProg <lgovedic@redhat.com>
Co-authored-by: Luka Govedič <lgovedic@redhat.com>
Co-authored-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
Co-authored-by: Robert Shaw <114415538+robertgshaw2-redhat@users.noreply.github.com>
Co-authored-by: Luka Govedič <luka.govedic@gmail.com>

Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
Signed-off-by: Matthew Bonanni <mbonanni001@gmail.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Lucas Wilkinson <LucasWilkinson@users.noreply.github.com>

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

Currently, when requests are cancelled while executing their final
step, "completion" is handled based on normal stop processing (e.g.
length or stop token), so the abort has no effect. This is typically
not a problem, but when a kv connector is involved it thinks the
request completed successfully rather than being aborted.

This is problematic for disaggregated prefill which will free kv
cache blocks if the request was aborted but not if it completed
successfully—since the cancelled request will never be sent to
the decode side, kv cache blocks remain pinned until the fall-back
timeout expires. The problem is exacerbated when many requests
are cancelled and/or there are large prefills whose forward pass
takes a long time (since the window is bigger).

This PR fixes the problem by processing pending aborts
immediately prior to processing model output each step; we process
only aborts, not new requests, since it's preferable for latency to
process model outputs before new incoming requests.

Fixes #26400.
Signed-off-by: Nick Hill <nhill@redhat.com>

Signed-off-by: NickLucche <nlucches@redhat.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>