Commits · afd0da2186c1d58fb48e138df0a2f548612b5d7d · OpenDAS / vllm_cscc

01 Feb, 2025 2 commits

Disable chunked prefill and/or prefix caching when MLA is enabled (#12642) · 4f4d427a

Simon Mo authored Jan 31, 2025

From @mgoin in https://github.com/vllm-project/vllm/pull/12638



I cannot push to that branch, therefore a new PR to unblock release.

---------
Signed-off-by: mgoin <michael@neuralmagic.com>
Signed-off-by: simon-mo <simon.mo@hey.com>
Co-authored-by: mgoin <michael@neuralmagic.com>

4f4d427a

[Attention] Deepseek v3 MLA support with FP8 compute (#12601) · baeded25

Lucas Wilkinson authored Feb 01, 2025



This PR implements the Deepseek V3 support by performing matrix absorption the fp8 weights 

---------
Signed-off-by: Lucas Wilkinson <lwilkinson@neuralmagic.com>
Co-authored-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
Co-authored-by: simon-mo <simon.mo@hey.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
Co-authored-by: Zhuohan Li <zhuohan123@gmail.com>
Co-authored-by: Tyler Michael Smith <tysmith@redhat.com>
Co-authored-by: Alexander Matveev <59768536+alexm-neuralmagic@users.noreply.github.com>

baeded25

31 Jan, 2025 1 commit

[Attention] MLA decode optimizations (#12528) · cabaf4ef

Lucas Wilkinson authored Jan 31, 2025


Signed-off-by: Lucas Wilkinson <lwilkinson@neuralmagic.com>
Signed-off-by: simon-mo <xmo@berkeley.edu>
Co-authored-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
Co-authored-by: simon-mo <simon.mo@hey.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
Co-authored-by: Zhuohan Li <zhuohan123@gmail.com>
Co-authored-by: Tyler Michael Smith <tysmith@redhat.com>
Co-authored-by: Alexander Matveev <59768536+alexm-neuralmagic@users.noreply.github.com>
Co-authored-by: simon-mo <xmo@berkeley.edu>

cabaf4ef

29 Jan, 2025 1 commit
- [Frontend] Support override generation config in args (#12409) · ff7424f4
  Yanyi Liu authored Jan 29, 2025
```
Signed-off-by: liuyanyi <wolfsonliu@163.com>
```
  ff7424f4
28 Jan, 2025 1 commit
- Update `pre-commit` hooks (#12475) · 823ab796
  Harry Mellor authored Jan 28, 2025
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  823ab796
27 Jan, 2025 2 commits

[Feature] [Spec decode]: Enable MLPSpeculator/Medusa and `prompt_logprobs`... · 6116ca8c

Nicolò Lucchesi authored Jan 27, 2025


[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>

6116ca8c

[FlashInfer] Upgrade to 0.2.0 (#11194) · 2bc3fbba

Bowen Wang authored Jan 28, 2025


Signed-off-by: Bowen Wang <abmfy@icloud.com>
Signed-off-by: youkaichao <youkaichao@gmail.com>
Co-authored-by: youkaichao <youkaichao@gmail.com>

2bc3fbba

26 Jan, 2025 1 commit

[Frontend] generation_config.json for maximum tokens(#12242) · 9ddc3522

Matthew Hendrey authored Jan 26, 2025


Signed-off-by: Matthew Hendrey <matthew.hendrey@gmail.com>
Signed-off-by: Shangming Cai <caishangming@linux.alibaba.com>
Signed-off-by: youkaichao <youkaichao@gmail.com>
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Signed-off-by: Yuan Tang <terrytangyuan@gmail.com>
Signed-off-by: Isotr0py <2037008807@qq.com>
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Signed-off-by: Chen Zhang <zhangch99@outlook.com>
Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
Co-authored-by: shangmingc <caishangming@linux.alibaba.com>
Co-authored-by: youkaichao <youkaichao@gmail.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Yuan Tang <terrytangyuan@gmail.com>
Co-authored-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
Co-authored-by: Chen Zhang <zhangch99@outlook.com>
Co-authored-by: wangxiyuan <wangxiyuan1007@gmail.com>

9ddc3522

24 Jan, 2025 1 commit
- [Misc] Remove deprecated code (#12383) · df5dafaa
  Cyrus Leung authored Jan 25, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  df5dafaa
23 Jan, 2025 2 commits
- [FP8][Kernel] Dynamic kv cache scaling factors computation (#11906) · e97f802b
  Gregory Shtrasberg authored Jan 23, 2025
```
Signed-off-by: Gregory Shtrasberg <Gregory.Shtrasberg@amd.com>
Co-authored-by: Micah Williamson <micah.williamson@amd.com>
```
  e97f802b
- [torch.compile] decouple compile sizes and cudagraph sizes (#12243) · 6e650f56
  youkaichao authored Jan 24, 2025
```
Signed-off-by: youkaichao <youkaichao@gmail.com>
```
  6e650f56
22 Jan, 2025 2 commits
- [Bugfix] Fix HPU multiprocessing executor (#12167) · 96f6a759
  Konrad Zawora authored Jan 22, 2025
```
Signed-off-by: Konrad Zawora <kzawora@habana.ai>
```
  96f6a759
- [Core] Support fully transparent sleep mode (#11743) · 68ad4e3a
  youkaichao authored Jan 22, 2025
```
Signed-off-by: youkaichao <youkaichao@gmail.com>
```
  68ad4e3a
21 Jan, 2025 2 commits

[torch.compile] transparent compilation with more logging (#12246) · c81081fe
youkaichao authored Jan 21, 2025
```
Signed-off-by: youkaichao <youkaichao@gmail.com>
```
c81081fe

[Kernel] optimize moe_align_block_size for cuda graph and large num_experts... · 750f4cab

Jinzhen Lin authored Jan 21, 2025


[Kernel] optimize moe_align_block_size for cuda graph and large num_experts (e.g. DeepSeek-V3) (#12222)
Signed-off-by: Jinzhen Lin <linjinzhen@hotmail.com>
Co-authored-by: Michael Goin <mgoin@redhat.com>
Co-authored-by: Tyler Michael Smith <tyler@neuralmagic.com>

750f4cab

19 Jan, 2025 1 commit
- [torch.compile] store inductor compiled Python file (#12182) · e66faf48
  youkaichao authored Jan 19, 2025
```
Signed-off-by: youkaichao <youkaichao@gmail.com>
```
  e66faf48
17 Jan, 2025 1 commit
- [BugFix] add more `is not None` check in VllmConfig.__post_init__ (#12138) · d1adb9b4
  Chen Zhang authored Jan 17, 2025
```
Signed-off-by: Chen Zhang <zhangch99@outlook.com>
```
  d1adb9b4
16 Jan, 2025 3 commits
- [Bugfix] Set enforce_eager automatically for mllama (#12127) · d06e8240
  Chen Zhang authored Jan 17, 2025
```
Signed-off-by: Chen Zhang <zhangch99@outlook.com>
```
  d06e8240
- Support torchrun and SPMD-style offline inference (#12071) · bf53e0c7
  youkaichao authored Jan 16, 2025
```
Signed-off-by: youkaichao <youkaichao@gmail.com>
```
  bf53e0c7
- [Bugfix] Remove hardcoded `head_size=256` for Deepseek v2 and v3 (#12067) · dd7c9ad8
  Isotr0py authored Jan 16, 2025
```
Signed-off-by: Isotr0py <2037008807@qq.com>
```
  dd7c9ad8
15 Jan, 2025 4 commits
- [V1][Core] Autotune encoder cache budget (#11895) · 70755e81
  Roger Wang authored Jan 15, 2025
```
Signed-off-by: Roger Wang <ywang@roblox.com>
```
  70755e81
- [Bugfix] use right truncation for non-generative tasks (#12050) · edce722e
  Joe Runde authored Jan 15, 2025
```
Signed-off-by: Joe Runde <Joseph.Runde@ibm.com>
```
  edce722e
- [Misc][Quark] Upstream Quark format to VLLM (#10765) · de0526f6
  kewang-xlnx authored Jan 16, 2025
```
Signed-off-by: kewang-xlnx <kewang@xilinx.com>
Signed-off-by: kewang2 <kewang2@amd.com>
Co-authored-by: kewang2 <kewang2@amd.com>
Co-authored-by: Michael Goin <michael@neuralmagic.com>
```
  de0526f6
- [core] platform agnostic executor via collective_rpc (#11256) · ad34c0df
  youkaichao authored Jan 15, 2025
```
Signed-off-by: youkaichao <youkaichao@gmail.com>
```
  ad34c0df
10 Jan, 2025 2 commits
- [Doc] [1/N] Initial guide for merged multi-modal processor (#11925) · 12664ddd
  Cyrus Leung authored Jan 10, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  12664ddd
- [torch.compile] Hide KV cache behind torch.compile boundary (#11677) · cf5f000d
  Chen Zhang authored Jan 10, 2025
```
Signed-off-by: Chen Zhang <zhangch99@outlook.com>
```
  cf5f000d
09 Jan, 2025 1 commit

[Misc] Move `print_*_once` from utils to logger (#11298) · d848800e

Cyrus Leung authored Jan 09, 2025

Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Signed-off-by: Maxime Fournioux <55544262+mfournioux@users.noreply.github.com>
Co-authored-by: Maxime Fournioux <55544262+mfournioux@users.noreply.github.com>

d848800e

08 Jan, 2025 4 commits
- [torch.compile] consider relevant code in compilation cache (#11614) · f1214117
  youkaichao authored Jan 08, 2025
```
Signed-off-by: youkaichao <youkaichao@gmail.com>
```
  f1214117
- [Hardware][Apple] Native support for macOS Apple Silicon (#11696) · cfd3219f
  Wallas Henrique authored Jan 08, 2025
```
Signed-off-by: Wallas Santos <wallashss@ibm.com>
Co-authored-by: Michael Goin <michael@neuralmagic.com>
```
  cfd3219f
- [Bug] Fix pickling of `ModelConfig` when RunAI Model Streamer is used (#11825) · ef68eb28
  Cyrus Leung authored Jan 08, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  ef68eb28
- [Bugfix] Add checks for LoRA and CPU offload (#11810) · f645eb69
  Jee Jee Li authored Jan 08, 2025
```
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
```
  f645eb69
06 Jan, 2025 2 commits
- [Doc][2/N] Reorganize Models and Usage sections (#11755) · ee77fdb5
  Cyrus Leung authored Jan 06, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  ee77fdb5
- [Bugfix] Remove block size constraint (#11723) · 408e5600
  Cody Yu authored Jan 05, 2025
  
  408e5600
03 Jan, 2025 1 commit
- [Model] Whisper model implementation (#11280) · e1a5c2f0
  Aurick Qiao authored Jan 03, 2025
```
Co-authored-by: Aurick Qiao <aurick.qiao@snowflake.com>
```
  e1a5c2f0
30 Dec, 2024 2 commits
- [platforms] enable platform plugins (#11602) · b12e87f9
  youkaichao authored Dec 30, 2024
```
Signed-off-by: youkaichao <youkaichao@gmail.com>
```
  b12e87f9
- [v1] fix compilation cache (#11598) · 3682e33f
  youkaichao authored Dec 30, 2024
```
Signed-off-by: youkaichao <youkaichao@gmail.com>
```
  3682e33f
29 Dec, 2024 1 commit
- [Misc] KV cache transfer connector registry (#11481) · faef77c0
  Kuntai Du authored Dec 29, 2024
```
Signed-off-by: KuntaiDu <kuntai@uchicago.edu>
```
  faef77c0
28 Dec, 2024 1 commit
- [bugfix] interleaving sliding window for cohere2 model (#11583) · 328841d0
  youkaichao authored Dec 29, 2024
```
Signed-off-by: youkaichao <youkaichao@gmail.com>
```
  328841d0
27 Dec, 2024 1 commit

Deepseek v3 (#11502) · f49777ba

Simon Mo authored Dec 26, 2024


Signed-off-by: mgoin <michael@neuralmagic.com>
Co-authored-by: mgoin <michael@neuralmagic.com>
Co-authored-by: robertgshaw2-neuralmagic <rshaw@neuralmagic.com>

f49777ba

26 Dec, 2024 1 commit

[Model] [Quantization] Support deepseek_v3 w8a8 fp8 block-wise quantization (#11523) · 2072924d

Michael Goin authored Dec 26, 2024


Signed-off-by: mgoin <michael@neuralmagic.com>
Signed-off-by: simon-mo <simon.mo@hey.com>
Signed-off-by: simon-mo <xmo@berkeley.edu>
Co-authored-by: simon-mo <simon.mo@hey.com>
Co-authored-by: simon-mo <xmo@berkeley.edu>
Co-authored-by: HandH1998 <1335248067@qq.com>

2072924d