Commits · 28e0750847ded93158a66efdcbc869d87463b38f · OpenDAS / vllm_cscc

27 Jan, 2025 1 commit
- [V1] Avoid list creation in input preparation (#12457) · 28e07508
  Woosuk Kwon authored Jan 26, 2025
```
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
```
  28e07508
26 Jan, 2025 1 commit
- [V1][Perf] Reduce scheduling overhead in model runner after cuda sync (#12094) · fa63e710
  Keyun Tong authored Jan 26, 2025
```
Signed-off-by: Keyun Tong <tongkeyun@gmail.com>
```
  fa63e710
23 Jan, 2025 3 commits
- [torch.compile] decouple compile sizes and cudagraph sizes (#12243) · 6e650f56
  youkaichao authored Jan 24, 2025
```
Signed-off-by: youkaichao <youkaichao@gmail.com>
```
  6e650f56
- [V1] Simplify M-RoPE (#12352) · 99d01a5e
  Roger Wang authored Jan 23, 2025
```
Signed-off-by: Roger Wang <ywang@roblox.com>
Co-authored-by: imkero <kerorek@outlook.com>
```
  99d01a5e
- [Kernel] Flash Attention 3 Support (#12093) · 978b45f3
  Lucas Wilkinson authored Jan 23, 2025
```
Signed-off-by: Lucas Wilkinson <lwilkinson@neuralmagic.com>
```
  978b45f3
21 Jan, 2025 1 commit
- [V1][Bugfix] Fix data item ordering in mixed-modality inference (#12259) · b197a5cc
  Roger Wang authored Jan 21, 2025
```
Signed-off-by: Roger Wang <ywang@roblox.com>
```
  b197a5cc
20 Jan, 2025 1 commit
- [Core] Interface for accessing model from `VllmRunner` (#10353) · 59a0192f
  Cyrus Leung authored Jan 20, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  59a0192f
19 Jan, 2025 1 commit

[V1] Add V1 support of Qwen2-VL (#12128) · 81763c58

Roger Wang authored Jan 19, 2025


Signed-off-by: Roger Wang <ywang@roblox.com>
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Co-authored-by: imkero <kerorek@outlook.com>
Co-authored-by: DarkLight1337 <tlleungac@connect.ust.hk>

81763c58

17 Jan, 2025 1 commit
- [V1] Move more control of kv cache initialization from model_executor to EngineCore (#11960) · 69d765f5
  Chen Zhang authored Jan 17, 2025
```
Signed-off-by: Chen Zhang <zhangch99@outlook.com>
Co-authored-by: Cody Yu <hao.yu.cody@gmail.com>
```
  69d765f5
15 Jan, 2025 1 commit
- [V1][Core] Autotune encoder cache budget (#11895) · 70755e81
  Roger Wang authored Jan 15, 2025
```
Signed-off-by: Roger Wang <ywang@roblox.com>
```
  70755e81
10 Jan, 2025 1 commit
- [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
06 Jan, 2025 2 commits

[V1] Extend beyond image modality and support mixed-modality inference with... · 91b361ae

Roger Wang authored Jan 06, 2025


[V1] Extend beyond image modality and support mixed-modality inference with Llava-OneVision (#11685)
Signed-off-by: Roger Wang <ywang@roblox.com>
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Co-authored-by: DarkLight1337 <tlleungac@connect.ust.hk>

91b361ae

[V1] Add BlockTable class (#11693) · 06bfb519
Woosuk Kwon authored Jan 06, 2025
```
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
```
06bfb519

04 Jan, 2025 1 commit
- [Core][Bugfix] Use correct device to initialize GPU data during CUDA-graph-capture (#11233) · 300acb83
  Yan Burman authored Jan 04, 2025
```
Signed-off-by: Yan Burman <yanburman@users.noreply.github.com>
Signed-off-by: Ido Asraff <idoa@atero.ai>
```
  300acb83
02 Jan, 2025 1 commit
- [V1][Minor] Optimize token_ids_cpu copy (#11692) · b55ed6ef
  Woosuk Kwon authored Jan 03, 2025
```
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
```
  b55ed6ef
01 Jan, 2025 1 commit
- [V1] Implement Cascade Attention (#11635) · 73001445
  Woosuk Kwon authored Jan 01, 2025
```
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
```
  73001445
31 Dec, 2024 1 commit

[V1][VLM] V1 support for selected single-image models. (#11632) · e7c7c5e8

Roger Wang authored Dec 31, 2024


Signed-off-by: Roger Wang <ywang@roblox.com>
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Signed-off-by: Isotr0py <2037008807@qq.com>
Co-authored-by: DarkLight1337 <tlleungac@connect.ust.hk>
Co-authored-by: Isotr0py <2037008807@qq.com>

e7c7c5e8

26 Dec, 2024 1 commit

[V1] Adding min tokens/repetition/presence/frequence penalties to V1 sampler (#10681) · dcb1a944

sroy745 authored Dec 26, 2024


Signed-off-by: Sourashis Roy <sroy@roblox.com>
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
Co-authored-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>

dcb1a944

20 Dec, 2024 1 commit
- [V1] Fix profiling for models with merged input processor (#11370) · 04139ade
  Roger Wang authored Dec 20, 2024
```
Signed-off-by: ywang96 <ywang@roblox.com>
```
  04139ade
19 Dec, 2024 1 commit
- [V1] Fix multimodal profiling for `Molmo` (#11325) · 7379b3d4
  Roger Wang authored Dec 19, 2024
```
Signed-off-by: ywang96 <ywang@example.com>
Co-authored-by: ywang96 <ywang@example.com>
```
  7379b3d4
18 Dec, 2024 1 commit
- [V1] VLM - enable processor cache by default (#11305) · fdea8ec1
  Alexander Matveev authored Dec 18, 2024
```
Signed-off-by: Alexander Matveev <alexm@neuralmagic.com>
```
  fdea8ec1
17 Dec, 2024 1 commit
- [V1][VLM] Proper memory profiling for image language models (#11210) · 59c9b6eb
  Roger Wang authored Dec 16, 2024
```
Signed-off-by: Roger Wang <ywang@roblox.com>
Co-authored-by: ywang96 <ywang@example.com>
```
  59c9b6eb
15 Dec, 2024 1 commit
- [V1][Minor] Cache np arange to reduce input preparation overhead (#11214) · 25ebed2f
  Woosuk Kwon authored Dec 15, 2024
```
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
```
  25ebed2f
14 Dec, 2024 1 commit
- Enable mypy checking on V1 code (#11105) · 6d917d0e
  Mark McLoughlin authored Dec 14, 2024
```
Signed-off-by: Mark McLoughlin <markmc@redhat.com>
```
  6d917d0e
13 Dec, 2024 1 commit
- [core] clean up cudagraph batchsize padding logic (#10996) · be39e3cd
  youkaichao authored Dec 12, 2024
```
Signed-off-by: youkaichao <youkaichao@gmail.com>
```
  be39e3cd
12 Dec, 2024 1 commit
- [V1] Use more persistent buffers to optimize input preparation overheads (#11111) · f092153f
  Woosuk Kwon authored Dec 11, 2024
```
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
```
  f092153f
11 Dec, 2024 2 commits
- [V1] Use input_ids as input for text-only models (#11032) · d643c2ab
  Woosuk Kwon authored Dec 11, 2024
```
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
```
  d643c2ab
- [Model] PP support for Mamba-like models (#10992) · ffa48c91
  Mor Zusman authored Dec 11, 2024
```
Signed-off-by: mzusman <mor.zusmann@gmail.com>
```
  ffa48c91
10 Dec, 2024 2 commits
- [torch.compile] add a flag to track batchsize statistics (#11059) · 75f89dc4
  youkaichao authored Dec 10, 2024
```
Signed-off-by: youkaichao <youkaichao@gmail.com>
```
  75f89dc4
- [V1] Multiprocessing Tensor Parallel Support for v1 (#9856) · 28b3a1c7
  Tyler Michael Smith authored Dec 10, 2024
```
Signed-off-by: Tyler Michael Smith <tyler@neuralmagic.com>
```
  28b3a1c7
09 Dec, 2024 2 commits

[v1] fix use compile sizes (#11000) · 1a2f8fb8
youkaichao authored Dec 09, 2024
```
Signed-off-by: youkaichao <youkaichao@gmail.com>
```
1a2f8fb8

[V1] Input Batch Relocation (#10962) · 25b79d9f

Varun Sundar Rabindranath authored Dec 09, 2024


Signed-off-by: Varun Sundar Rabindranath <varun@neuralmagic.com>
Co-authored-by: Varun Sundar Rabindranath <varun@neuralmagic.com>

25b79d9f

05 Dec, 2024 1 commit
- [V1] Fix when max_model_len is not divisible by block_size (#10903) · 2a56e126
  Woosuk Kwon authored Dec 04, 2024
```
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
```
  2a56e126
03 Dec, 2024 1 commit
- [torch.compile] remove compilation_context and simplify code (#10838) · dc5ce861
  youkaichao authored Dec 02, 2024
```
Signed-off-by: youkaichao <youkaichao@gmail.com>
```
  dc5ce861
26 Nov, 2024 2 commits
- [V1] Refactor model executable interface for multimodal models (#10570) · 2f0a0a17
  Roger Wang authored Nov 26, 2024
```
Signed-off-by: Roger Wang <ywang@roblox.com>
```
  2f0a0a17
- custom allreduce + torch.compile (#10121) · 9a88f897
  Sage Moore authored Nov 26, 2024
```
Signed-off-by: youkaichao <youkaichao@gmail.com>
Co-authored-by: youkaichao <youkaichao@gmail.com>
```
  9a88f897
22 Nov, 2024 1 commit
- [torch.compile] support all attention backends (#10558) · eebad39f
  youkaichao authored Nov 22, 2024
```
Signed-off-by: youkaichao <youkaichao@gmail.com>
```
  eebad39f
21 Nov, 2024 2 commits
- [V1] Fix Compilation config & Enable CUDA graph by default (#10528) · f9310cbd
  Woosuk Kwon authored Nov 21, 2024
```
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
```
  f9310cbd
- [torch.compile] Inductor code caching fix (#10273) · 8b0fe06c
  Luka Govedič authored Nov 21, 2024
```
Signed-off-by: luka <luka@neuralmagic.com>
Signed-off-by: Luka Govedic <luka.govedic@gmail.com>
```
  8b0fe06c
19 Nov, 2024 1 commit
- [6/N] torch.compile rollout to users (#10437) · 803f37ea
  youkaichao authored Nov 19, 2024
```
Signed-off-by: youkaichao <youkaichao@gmail.com>
```
  803f37ea