Commits · 6d646d08a2e0e73e83e313a5ae470c1f9e4f200e · OpenDAS / vllm_cscc

03 Sep, 2024 1 commit
- [Core] Optimize Async + Multi-step (#8050) · 6d646d08
  Alexander Matveev authored Sep 03, 2024
  
  6d646d08
30 Aug, 2024 1 commit
- [Core] Logprobs support in Multi-step (#7652) · 428dd144
  afeldman-nm authored Aug 29, 2024
  
  428dd144
29 Aug, 2024 3 commits
- extend cuda graph size for H200 (#7894) · c334b189
  kushanam authored Aug 29, 2024
```
Co-authored-by: youkaichao <youkaichao@126.com>
```
  c334b189
- [Core] Combine async postprocessor and multi-step (#7921) · 3f60f224
  Alexander Matveev authored Aug 29, 2024
  
  3f60f224
- [torch.compile] remove reset (#7975) · a7f65c2b
  youkaichao authored Aug 28, 2024
  
  a7f65c2b
28 Aug, 2024 3 commits
- [Performance] Enable chunked prefill and prefix caching together (#7753) · e3580537
  Cody Yu authored Aug 28, 2024
  
  e3580537
- [Core] Async_output_proc: Add virtual engine support (towards pipeline parallel) (#7911) · f508e03e
  Alexander Matveev authored Aug 28, 2024
  
  f508e03e
- [Bugfix] Allow ScalarType to be compiled with pytorch 2.3 and add checks for... · c166e7e4
  bnellnm authored Aug 27, 2024
```
[Bugfix] Allow ScalarType to be compiled with pytorch 2.3 and add checks for registering FakeScalarType and dynamo support. (#7886)
```
  c166e7e4
27 Aug, 2024 2 commits
- [core][torch.compile] discard the compile for profiling (#7796) · 64cc6444
  youkaichao authored Aug 26, 2024
  
  64cc6444
- [Core] Asynchronous Output Processor (#7049) · 2eedede8
  Megha Agarwal authored Aug 26, 2024
```
Co-authored-by: Alexander Matveev <alexm@neuralmagic.com>
```
  2eedede8
22 Aug, 2024 1 commit
- [Speculative Decoding] EAGLE Implementation with Top-1 proposer (#6830) · a3fce56b
  Abhinav Goyal authored Aug 22, 2024
  
  a3fce56b
20 Aug, 2024 1 commit
- [Core] Add `AttentionState` abstraction (#7663) · 3b682179
  Antoni Baum authored Aug 20, 2024
  
  3b682179
17 Aug, 2024 1 commit
- [VLM] Refactor `MultiModalConfig` initialization and profiling (#7530) · bbf55c48
  Roger Wang authored Aug 17, 2024
  
  bbf55c48
16 Aug, 2024 1 commit
- [Core] Fix tracking of model forward time in case of PP>1 (#7440) · 93478b63
  Mahesh Keralapura authored Aug 16, 2024
```
[Core] Fix tracking of model forward time to the span traces in case of PP>1 (#7440)
```
  93478b63
14 Aug, 2024 1 commit
- [VLM][Core] Support profiling with multiple multi-modal inputs per prompt (#7126) · 3f674a49
  Cyrus Leung authored Aug 15, 2024
  
  3f674a49
13 Aug, 2024 1 commit
- [Frontend][Core] Add plumbing to support audio language models (#7446) · 00c3d68e
  Peter Salas authored Aug 13, 2024
  
  00c3d68e
09 Aug, 2024 4 commits
- [Core] Add span metrics for model_forward, scheduler and sampler time (#7089) · 933790c2
  Mahesh Keralapura authored Aug 09, 2024
  
  933790c2
- [Bugfix] Fix reinit procedure in ModelInputForGPUBuilder (#7360) · 74af2bbd
  Alexander Matveev authored Aug 09, 2024
  
  74af2bbd
- [Model][Jamba] Mamba cache single buffer (#6739) · 07ab1607
  Mor Zusman authored Aug 09, 2024
```
Co-authored-by: Mor Zusman <morz@ai21.com>
```
  07ab1607
- [Performance] Optimize e2e overheads: Reduce python allocations (#7162) · e02ac556
  Alexander Matveev authored Aug 09, 2024
  
  e02ac556
05 Aug, 2024 1 commit
- [MISC] Use non-blocking transfer in prepare_input (#7172) · ef527be0
  Cody Yu authored Aug 05, 2024
  
  ef527be0
02 Aug, 2024 1 commit
- [misc] add a flag to enable compile (#7092) · 70898934
  youkaichao authored Aug 02, 2024
  
  70898934
01 Aug, 2024 1 commit
- [Kernel][RFC] Refactor the punica kernel based on Triton (#5036) · 7ecee343
  Jee Jee Li authored Aug 01, 2024
  
  7ecee343
31 Jul, 2024 1 commit
- [Bugfix] Fix broadcasting logic for `multi_modal_kwargs` (#6836) · f230cc2c
  Cyrus Leung authored Jul 31, 2024
  
  f230cc2c
30 Jul, 2024 1 commit
- [BugFix] Fix use of per-request seed with pipeline parallel (#6698) · 5cf9254a
  Nick Hill authored Jul 30, 2024
  
  5cf9254a
24 Jul, 2024 2 commits
- [Core] Tweaks to model runner/input builder developer APIs (#6712) · 5448f676
  Antoni Baum authored Jul 24, 2024
  
  5448f676
- [Bugfix] fix flashinfer cudagraph capture for PP (#6708) · 5e8ca973
  William Lin authored Jul 23, 2024
  
  5e8ca973
23 Jul, 2024 2 commits
- [misc] add start loading models for users information (#6670) · 7c2749a4
  youkaichao authored Jul 22, 2024
  
  7c2749a4
- [Core] Modulize prepare input and attention metadata builder (#6596) · e0c15758
  Cody Yu authored Jul 22, 2024
  
  e0c15758
22 Jul, 2024 1 commit
- [Core] Support dynamically loading Lora adapter from HuggingFace (#6234) · 42c7f66a
  Jiaxin Shan authored Jul 22, 2024
```
Co-authored-by: Antoni Baum <antoni.baum@protonmail.com>
```
  42c7f66a
18 Jul, 2024 1 commit
- [core][model] yet another cpu offload implementation (#6496) · 1c27d25f
  youkaichao authored Jul 17, 2024
```
Co-authored-by: Michael Goin <michael@neuralmagic.com>
```
  1c27d25f
17 Jul, 2024 1 commit
- [Core] Refactor _prepare_model_input_tensors - take 2 (#6164) · 2fa4623d
  Cody Yu authored Jul 17, 2024
  
  2fa4623d
09 Jul, 2024 1 commit

[CORE] Adding support for insertion of soft-tuned prompts (#4645) · 4d6ada94

Swapnil Parekh authored Jul 09, 2024


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>

4d6ada94

04 Jul, 2024 2 commits
- [VLM] Calculate maximum number of multi-modal tokens by model (#6121) · ae96ef8f
  Cyrus Leung authored Jul 05, 2024
  
  ae96ef8f
- [Kernel][Model] logits_soft_cap for Gemma2 with flashinfer (#6051) · 69ec3ca1
  Lily Liu authored Jul 04, 2024
```
Co-authored-by: Simon Mo <simon.mo@hey.com>
```
  69ec3ca1
03 Jul, 2024 2 commits

[vlm] Remove vision language config. (#6089) · d9e98f42

xwjiang2010 authored Jul 03, 2024


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

d9e98f42

[Core] Dynamic image size support for VLMs (#5276) · 9831aec4

Cyrus Leung authored Jul 03, 2024


Signed-off-by: Xiaowei Jiang <xwjiang2010@gmail.com>
Co-authored-by: Xiaowei Jiang <xwjiang2010@gmail.com>
Co-authored-by: ywang96 <ywang@roblox.com>
Co-authored-by: xwjiang2010 <87673679+xwjiang2010@users.noreply.github.com>
Co-authored-by: Roger Wang <136131678+ywang96@users.noreply.github.com>

9831aec4

02 Jul, 2024 3 commits

[Model] Jamba support (#4115) · 9d6a8daa

Mor Zusman authored Jul 03, 2024


Signed-off-by: Muralidhar Andoorveedu <muralidhar.andoorveedu@centml.ai>
Co-authored-by: Erez Schwartz <erezs@ai21.com>
Co-authored-by: Mor Zusman <morz@ai21.com>
Co-authored-by: tomeras91 <57313761+tomeras91@users.noreply.github.com>
Co-authored-by: Tomer Asida <tomera@ai21.com>
Co-authored-by: Zhuohan Li <zhuohan123@gmail.com>
Co-authored-by: Muralidhar Andoorveedu <muralidhar.andoorveedu@centml.ai>

9d6a8daa

[Core] Pipeline Parallel Support (#4412) · c5832d2a
Murali Andoorveedu authored Jul 02, 2024
```
Signed-off-by: Muralidhar Andoorveedu <muralidhar.andoorveedu@centml.ai>
```
c5832d2a

[VLM] Remove `image_input_type` from VLM config (#5852) · 98d6682c

xwjiang2010 authored Jul 02, 2024


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>

98d6682c