Commits · 4d51588e2381018348f1022dfa3a7698899805b7 · OpenDAS / vllm_cscc

27 Apr, 2026 1 commit

[Feat] DeepSeek V4 Rebased (#40860) · 4d51588e

Yifan Qiao authored Apr 26, 2026


Signed-off-by: Yifan Qiao <yifanqiao@inferact.ai>
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
Signed-off-by: qizixi <zixi@inferact.ai>
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
Signed-off-by: Yongye Zhu <zyy1102000@gmail.com>
Co-authored-by: Yongye Zhu <zyy1102000@gmail.com>
Co-authored-by: Yongye Zhu <yongye@inferact.ai>
Co-authored-by: Simon Mo <simon@inferact.ai>
Co-authored-by: Bugen Zhao <i@bugenzhao.com>
Co-authored-by: Giancarlo Delfin <gdelfin@inferact.ai>
Co-authored-by: Jee Jee Li <pandaleefree@gmail.com>
Co-authored-by: Nick Hill <nickhill123@gmail.com>
Co-authored-by: Roger Wang <hey@rogerw.io>
Co-authored-by: Roy Wang <yasong.wang@inferact.ai>
Co-authored-by: Woosuk Kwon <woosuk@inferact.ai>
Co-authored-by: youkaichao <youkaichao@gmail.com>
Co-authored-by: Zhewen Li <jerven.vllm@gmail.com>
Co-authored-by: Zijing Liu <liuzijing2014@gmail.com>
Co-authored-by: khluu <khluu000@gmail.com>
Co-authored-by: qizixi <zixi@inferact.ai>
Co-authored-by: Zhewen Li <zhewenli@inferact.ai>

4d51588e

16 Apr, 2026 1 commit
- [Mistral Grammar] Fix tool and reasoning parsing (#39217) · c0722f22
  Julien Denize authored Apr 16, 2026
```
Signed-off-by: juliendenize <julien.denize@mistral.ai>
```
  c0722f22
15 Apr, 2026 1 commit

Update to transformers v5 (#30566) · 03f8d3a5

Harry Mellor authored Apr 16, 2026


Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Signed-off-by: khluu <khluu000@gmail.com>
Signed-off-by: Kevin H. Luu <khluu000@gmail.com>
Signed-off-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
Co-authored-by: khluu <khluu000@gmail.com>
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
Co-authored-by: jiang1.li <jiang1.li@intel.com>

03f8d3a5

06 Apr, 2026 1 commit
- [Mistral Grammar] Support Grammar Factory (#38150) · fef56c18
  Julien Denize authored Apr 06, 2026
```
Signed-off-by: juliendenize <julien.denize@mistral.ai>
```
  fef56c18
17 Mar, 2026 2 commits
- [Bugfix] Standardize custom HF Processor init (#37289) · c781fbba
  Cyrus Leung authored Mar 17, 2026
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  c781fbba
- Fix some Mistral parser issues (#37209) · 5db91f0a
  Julien Denize authored Mar 17, 2026
```
Signed-off-by: juliendenize <julien.denize@mistral.ai>
```
  5db91f0a
14 Mar, 2026 1 commit

Mistral common v10 (#36971) · e42b49bd

Julien Denize authored Mar 14, 2026

Signed-off-by: juliendenize <julien.denize@mistral.ai>
Signed-off-by: Julien Denize <40604584+juliendenize@users.noreply.github.com>
Co-authored-by: root <root@h200-bar-196-227.slurm-bar-compute.tenant-slurm.svc.cluster.local>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>

e42b49bd

13 Mar, 2026 1 commit
- [Bugfix] Fix DeepSeek-V3.2 tokenizer stripping spaces (#37004) · 9efc4db9
  Matthew Bonanni authored Mar 13, 2026
```
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
```
  9efc4db9
12 Mar, 2026 2 commits

[CI] Fix mypy pre-commit errors on main (#36882) · abcffbba

Thomas Parnell authored Mar 12, 2026


Signed-off-by: Thomas Parnell <tpa@zurich.ibm.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>

abcffbba

[CI] Fix mypy for vllm/reasoning (#35742) · 7f1f36bf

Martin Hickey authored Mar 12, 2026

Signed-off-by: Martin Hickey <martin.hickey@ie.ibm.com>
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>

7f1f36bf

11 Mar, 2026 3 commits

[Misc] Clean up renderers (#36770) · 196802df
Cyrus Leung authored Mar 12, 2026
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
196802df
[Doc] Fix duplicate words in comments (#36713) · 4bf53362
Hongbin Guo authored Mar 11, 2026
```
Signed-off-by: Hongbin10 <jdmjdm1998@163.com>
```
4bf53362

[Model] Add support for moonshotai/Kimi-Audio-7B-Instruct (#36127) · 42fadebe

tunglinwood authored Mar 11, 2026


Signed-off-by: tunglinwood <tunglinwood@gmail.com>
Signed-off-by: tunglinwood <tomwu.tunglin@gmail.com>
Signed-off-by: tunglinwood <113751333+tunglinwood@users.noreply.github.com>

42fadebe

05 Mar, 2026 2 commits

[Bugfix][CI] fix typos (#34934) · 6a895197

Jiayi Yan authored Mar 06, 2026

Signed-off-by: 1195343015 <1195343015@qq.com>
Signed-off-by: Jiayi Yan <66017932+1195343015@users.noreply.github.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>

6a895197

[Bugfix] Fix Qwen-VL tokenizer implementation (#36140) · 71963481
Cyrus Leung authored Mar 06, 2026
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
71963481

23 Feb, 2026 1 commit
- [Feature] Lazy import for the "mistral" tokenizer module. (#34651) · 54e2f83d
  Neil Schemenauer authored Feb 23, 2026
```
Signed-off-by: Neil Schemenauer <nas@arctrix.com>
```
  54e2f83d
14 Feb, 2026 2 commits
- [CI] Heavy refactoring of Voxtral multimodal audio model tests (#34294) · de42abb3
  Andreas Karatzas authored Feb 13, 2026
```
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
```
  de42abb3
- Add explicit validation error for tool calls. (#34438) · 60ca7981
  Julien Denize authored Feb 14, 2026
```
Signed-off-by: juliendenize <julien.denize@mistral.ai>
```
  60ca7981
08 Feb, 2026 1 commit
- [Perf] Simplify DeepseekV32 tokenizer, ensure fast detokenization used (#33855) · a96197f5
  Nick Hill authored Feb 07, 2026
```
Signed-off-by: Nick Hill <nickhill123@gmail.com>
```
  a96197f5
06 Feb, 2026 1 commit

feat(frontend): early-fail tokenization guard for user requests (#31366) · a32cb49b

Mingliang Li authored Feb 06, 2026


Signed-off-by: limingliang <limingliang@stepfun.com>
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Co-authored-by: limingliang <limingliang@stepfun.com>
Co-authored-by: DarkLight1337 <tlleungac@connect.ust.hk>

a32cb49b

05 Feb, 2026 1 commit
- [Bugfix] Fix DeepSeek v3.2 tokenizer outputting None issue (#33832) · 91a07ff6
  Wei Zhao authored Feb 05, 2026
```
Signed-off-by: wzhao18 <wzhao18.sz@gmail.com>
```
  91a07ff6
30 Jan, 2026 3 commits

Improve Mistral format checks. (#33253) · ae5b7aff

Julien Denize authored Jan 30, 2026


Signed-off-by: Julien Denize <julien.denize@mistral.ai>
Signed-off-by: juliendenize <julien.denize@mistral.ai>
Co-authored-by: Michael Goin <mgoin64@gmail.com>

ae5b7aff

Remove deprecated `reasoning_content` message field (#33402) · c5113f60
Harry Mellor authored Jan 30, 2026
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
c5113f60
Explicitly set `return_dict` for `apply_chat_template` (#33372) · 9432ed8c
Harry Mellor authored Jan 30, 2026
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
9432ed8c

23 Jan, 2026 1 commit
- [BugFix] deepseek_v32_encoding: Replace asserts with proper exceptions (#32884) · f61c9da7
  Rishabh Saini authored Jan 22, 2026
```
Signed-off-by: RishabhSaini <rishabhsaini01@gmail.com>
```
  f61c9da7
13 Jan, 2026 1 commit
- [Refactor] [6/N] to simplify the vLLM openai chat_completion serving architecture (#32240) · fefce498
  Chauncey authored Jan 13, 2026
```
Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>
```
  fefce498
08 Jan, 2026 1 commit
- [Model] Add Grok-2 (#31847) · 59d260f5
  Bijaya Dangol authored Jan 08, 2026
```
Signed-off-by: dangoldbj <dangoldbj23@gmail.com>
```
  59d260f5
06 Jan, 2026 1 commit
- [Misc] Implement `TokenizerLike.convert_tokens_to_ids` (#31796) · 64448248
  Cyrus Leung authored Jan 06, 2026
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  64448248
05 Jan, 2026 1 commit
- Add chat prefix completion feature to DeepSeek v3.2 (#31147) · 346e5645
  CHENYUE authored Jan 05, 2026
  
  346e5645
26 Dec, 2025 1 commit

[Mistral common] Ensure all functions are imported from the top & only use public methods (#31138) · 48e74497

Patrick von Platen authored Dec 26, 2025

Signed-off-by: Patrick von Platen <patrick.v.platen@gmail.com>
Co-authored-by: Julien Denize <40604584+juliendenize@users.noreply.github.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>

48e74497

24 Dec, 2025 1 commit
- [Chore][1/2] Drop `v0.14` deprecations (#31285) · 09dc7c69
  Cyrus Leung authored Dec 25, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  09dc7c69
17 Dec, 2025 1 commit
- Adapt the old parameter enable_thinking in chat_template_kwargs (#30852) · b7b6a60a
  高鑫崧 authored Dec 17, 2025
```
Signed-off-by: xinsong.gao <1418762819@qq.com>
Co-authored-by: Chauncey <chaunceyjiang@gmail.com>
```
  b7b6a60a
15 Dec, 2025 1 commit
- [Bugfix] Fix deepseek_v32 tokenizer_mode (#30658) · a524d1ba
  Jee Jee Li authored Dec 15, 2025
```
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
```
  a524d1ba
13 Dec, 2025 1 commit
- [Refactor] `TokenizerRegistry` only uses lazy imports (#30609) · 39cefbdf
  Cyrus Leung authored Dec 13, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  39cefbdf
12 Dec, 2025 1 commit
- [DeepSeek V3.2] Proper drop_thinking logic (#30490) · 3e34adcd
  Vladislav Nosivskoy authored Dec 12, 2025
```
Signed-off-by: Vladislav Nosivskoy <vladnosiv@gmail.com>
```
  3e34adcd
10 Dec, 2025 1 commit
- [Bugfix] Cache added_vocab to avoid per-token overhead (#30351) · d007387a
  Mingliang Li authored Dec 10, 2025
```
Signed-off-by: limingliang <limingliang@stepfun.com>
Co-authored-by: limingliang <limingliang@stepfun.com>
```
  d007387a
07 Dec, 2025 2 commits
- Revert "[Renderer] Separate out `RendererConfig` from `ModelConfig` (#30145)" (#30199) · e83b7e37
  Cyrus Leung authored Dec 07, 2025
  
  e83b7e37
- [Renderer] Separate out `RendererConfig` from `ModelConfig` (#30145) · 27f4c2fd
  Cyrus Leung authored Dec 07, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  27f4c2fd
06 Dec, 2025 1 commit
- [Bugfix]: Fix `TokenizerLike` interface (#30009) · 40a046cd
  Rohan Potdar authored Dec 05, 2025
```
Signed-off-by: Rohan138 <rohanpotdar138@gmail.com>
```
  40a046cd
04 Dec, 2025 1 commit

[Bugfix] fixed deepseekv32 tool calling error (#30025) · 82a64b3d

Chauncey authored Dec 04, 2025


Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>

82a64b3d