GitLab

[Feature] [Spec decode]: Enable MLPSpeculator/Medusa and `prompt_logprobs` with ChunkedPrefill (#10132)
Signed-off-by: NickLucche <nlucches@redhat.com>
Signed-off-by: wallashss <wallashss@ibm.com>
Co-authored-by: wallashss <wallashss@ibm.com>

Signed-off-by: youkaichao <youkaichao@gmail.com>

[Bugfix][SpecDecode] apply sampling parameters to target probabilities for consistency in rejection sampling. (#10198)
Signed-off-by: jeongin601 <0200angela@gmail.com>
Signed-off-by: jeong_in.bae <jeong_in.bae@navercorp.com>

Signed-off-by: andoorve <37849411+andoorve@users.noreply.github.com>
Signed-off-by: Sourashis Roy <sroy@roblox.com>
Co-authored-by: Sourashis Roy <sroy@roblox.com>

Signed-off-by: Sourashis Roy <sroy@roblox.com>

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

Signed-off-by: wangshuai09 <391746016@qq.com>

Removing the block manager v1. This is the initial piece of prefix-caching-centric design. In order to achieve prefix-caching-centric design, we need to simplify the code path so that we only use v2 block manager (which has much higher performance on prefix caching).

[Core] Add an environment variable which needs to be set explicitly to allow BlockSpaceManagerV1 (#9149)

Signed-off-by: Travis Johnson <tsjohnso@us.ibm.com>

Co-authored-by: youkaichao <youkaichao@126.com>

Signed-off-by: Travis Johnson <tsjohnso@us.ibm.com>

Signed-off-by: Wallas Santos <wallashss@ibm.com>
Co-authored-by: youkaichao <youkaichao@gmail.com>
Co-authored-by: Nick Hill <nickhill@us.ibm.com>
Co-authored-by: youkaichao <youkaichao@126.com>

Signed-off-by: Travis Johnson <tsjohnso@us.ibm.com>

[Spec Decode] Disable Log Prob serialization to CPU for spec decoding for both draft and target models. (#6485)

Signed-off-by: Thomas Parnell <tpa@zurich.ibm.com>

Signed-off-by: Thomas Parnell <tpa@zurich.ibm.com>
Co-authored-by: Nick Hill <nickhill@us.ibm.com>

Co-authored-by: Swapnil Parekh <swapnilp@ibm.com>
Co-authored-by: Joe G <joseph.granados@h2o.ai>
Co-authored-by: Antoni Baum <antoni.baum@protonmail.com>

Co-authored-by: Robert Shaw <rshaw@neuralmagic.com>
Co-authored-by: ZX <zx@lbx.dev>

Co-authored-by: Sirej Dua <sirej.dua@databricks.com>
Co-authored-by: Sirej Dua <Sirej Dua>

Signed-off-by: Xiaowei Jiang <xwjiang2010@gmail.com>
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
Co-authored-by: Roger Wang <ywang@roblox.com>

Signed-off-by: Thomas Parnell <tpa@zurich.ibm.com>

 [Speculative Decoding] Support draft model on different tensor-parallel size than target model (#5414)