Commits · e2b2aa5a0fdd3e682dd1fbd62e2ba81b8aa054d2 · OpenDAS / vllm_cscc · GitLab

02 Sep, 2024 1 commit
- [TPU] Align worker index with node boundary (#7932) · e2b2aa5a
  Woosuk Kwon authored Sep 01, 2024
  
  e2b2aa5a
30 Aug, 2024 2 commits
- [TPU] Support single and multi-host TPUs on GKE (#7613) · 2148441f
  Richard Liu authored Aug 30, 2024
  
  2148441f
- [Core] Logprobs support in Multi-step (#7652) · 428dd144
  afeldman-nm authored Aug 29, 2024
  
  428dd144
28 Aug, 2024 1 commit
- [ci][test] fix pp test failure (#7945) · f52a43a8
  youkaichao authored Aug 28, 2024
  
  f52a43a8
27 Aug, 2024 2 commits
- [Hardware][Intel GPU] Add intel GPU pipeline parallel support. (#7810) · 076169f6
  Kunshang Ji authored Aug 28, 2024
  
  076169f6
- [Core] Asynchronous Output Processor (#7049) · 2eedede8
  Megha Agarwal authored Aug 26, 2024
```
Co-authored-by: Alexander Matveev <alexm@neuralmagic.com>
```
  2eedede8
26 Aug, 2024 1 commit
- [Bugfix] neuron: enable tensor parallelism (#7562) · 760e9f71
  omrishiv authored Aug 26, 2024
```
Signed-off-by: omrishiv <327609+omrishiv@users.noreply.github.com>
```
  760e9f71
23 Aug, 2024 2 commits
- [Hardware][Intel GPU] refactor xpu_model_runner for tp (#7712) · fc5ebbd1
  Kunshang Ji authored Aug 23, 2024
  
  fc5ebbd1
- [Ray backend] Better error when pg topology is bad. (#7584) · c01a6cb2
  SangBin Cho authored Aug 22, 2024
```
Co-authored-by: youkaichao <youkaichao@126.com>
```
  c01a6cb2
21 Aug, 2024 2 commits
- [distributed][misc] error on same VLLM_HOST_IP setting (#7756) · 7eebe8cc
  youkaichao authored Aug 21, 2024
  
  7eebe8cc
- [Core] Pipe `worker_class_fn` argument in Executor (#7707) · 66a9e713
  Antoni Baum authored Aug 20, 2024
  
  66a9e713
20 Aug, 2024 2 commits
- [Hardware] [Intel GPU] refactor xpu worker/executor (#7686) · c42590f9
  Kunshang Ji authored Aug 21, 2024
  
  c42590f9
- [Core] Refactor executor classes for easier inheritance (#7673) · b6f99a6f
  Kunshang Ji authored Aug 20, 2024
```
[Core] Refactor executor classes to make it easier to inherit GPUExecutor (#7673)
```
  b6f99a6f
19 Aug, 2024 2 commits
- [core] Multi Step Scheduling (#7000) · 47b65a55
  William Lin authored Aug 19, 2024
```
Co-authored-by: afeldman-nm <156691304+afeldman-nm@users.noreply.github.com>
```
  47b65a55
- [Core] Optimize SPMD architecture with delta + serialization optimization (#7109) · ff7ec82c
  SangBin Cho authored Aug 18, 2024
  
  ff7ec82c
17 Aug, 2024 1 commit
- [VLM] Refactor `MultiModalConfig` initialization and profiling (#7530) · bbf55c48
  Roger Wang authored Aug 17, 2024
  
  bbf55c48
15 Aug, 2024 1 commit

[Bugfix] update neuron for version > 0.5.0 (#7175) · 9c1f78d5

omrishiv authored Aug 15, 2024


Signed-off-by: omrishiv <327609+omrishiv@users.noreply.github.com>
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>

9c1f78d5

13 Aug, 2024 2 commits
- [hardware] unify usage of is_tpu to current_platform.is_tpu() (#7102) · 4d2dc507
  youkaichao authored Aug 13, 2024
  
  4d2dc507
- [Core] Shut down aDAG workers with clean async llm engine exit (#7224) · 198d6a28
  Rui Qiao authored Aug 12, 2024
```
Signed-off-by: Rui Qiao <ruisearch42@gmail.com>
```
  198d6a28
12 Aug, 2024 1 commit
- [Core] Consolidate `GB` constant and enable float GB arguments (#7416) · 4ddc4743
  Cyrus Leung authored Aug 13, 2024
  
  4ddc4743
09 Aug, 2024 1 commit
- [Core] Add span metrics for model_forward, scheduler and sampler time (#7089) · 933790c2
  Mahesh Keralapura authored Aug 09, 2024
  
  933790c2
02 Aug, 2024 3 commits
- [Misc] Revive to use loopback address for driver IP (#7091) · 22e718ff
  Rui Qiao authored Aug 02, 2024
```
Signed-off-by: Rui Qiao <ruisearch42@gmail.com>
```
  22e718ff
- [Core] Pipeline parallel with Ray ADAG (#6837) · 05308891
  Rui Qiao authored Aug 02, 2024
```
Support pipeline-parallelism with Ray accelerated DAG.
Signed-off-by: Rui Qiao <ruisearch42@gmail.com>
```
  05308891
- [cuda][misc] remove error_on_invalid_device_count_status (#7069) · 660dea12
  youkaichao authored Aug 02, 2024
  
  660dea12
27 Jul, 2024 2 commits
- [Bugfix] torch.set_num_threads() in multiproc_gpu_executor (#6802) · 593e79e7
  Travis Johnson authored Jul 26, 2024
```
[Bugfix] Use torch.set_num_threads() to configure parallelism in multiproc_gpu_executor (#6802)
Signed-off-by: Travis Johnson <tsjohnso@us.ibm.com>
```
  593e79e7
- [Hardware][TPU] Implement tensor parallelism with Ray (#5871) · 52f07e3d
  Woosuk Kwon authored Jul 26, 2024
  
  52f07e3d
26 Jul, 2024 3 commits
- [Hardware] [Intel] Enable Multiprocessing and tensor parallel in CPU backend... · 3bbb4936
  Li, Jiang authored Jul 27, 2024
```
[Hardware] [Intel] Enable Multiprocessing and tensor parallel in CPU backend and update documentation  (#6125)
```
  3bbb4936
- [Misc][TPU] Support TPU in initialize_ray_cluster (#6812) · aa486779
  Woosuk Kwon authored Jul 26, 2024
  
  aa486779
- [Bugfix] [Easy] Fixed a bug in the multiprocessing GPU executor. (#6770) · 084a01fd
  Anthony Platanios authored Jul 26, 2024
  
  084a01fd
25 Jul, 2024 1 commit
- [Core] Fix ray forward_dag error mssg (#6792) · 1adddb14
  SangBin Cho authored Jul 25, 2024
  
  1adddb14
20 Jul, 2024 1 commit
- [Core] Allow specifying custom Executor (#6557) · 7bd82002
  Antoni Baum authored Jul 19, 2024
  
  7bd82002
19 Jul, 2024 1 commit
- [Core] Multiprocessing Pipeline Parallel support (#6130) · b5672a11
  Nick Hill authored Jul 18, 2024
```
Co-authored-by: Murali Andoorveedu <muralidhar.andoorveedu@centml.ai>
```
  b5672a11
18 Jul, 2024 1 commit
- [Core] Introduce SPMD worker execution using Ray accelerated DAG (#6032) · 61e59274
  Rui Qiao authored Jul 17, 2024
```
Signed-off-by: Rui Qiao <ruisearch42@gmail.com>
Co-authored-by: Stephanie Wang <swang@cs.berkeley.edu>
```
  61e59274
17 Jul, 2024 1 commit
- [Bugfix] Fix for multinode crash on 4 PP (#6495) · 5fa6e987
  Murali Andoorveedu authored Jul 17, 2024
```
Signed-off-by: Muralidhar Andoorveedu <muralidhar.andoorveedu@centml.ai>
```
  5fa6e987
16 Jul, 2024 1 commit
- [ci][distributed] add pipeline parallel correctness test (#6410) · 09c2eb85
  youkaichao authored Jul 16, 2024
  
  09c2eb85
15 Jul, 2024 1 commit
- [Bugfix] Add custom Triton cache manager to resolve MoE MP issue (#6140) · eaec4b91
  Thomas Parnell authored Jul 15, 2024
```
Signed-off-by: Thomas Parnell <tpa@zurich.ibm.com>
Co-authored-by: Chih-Chieh-Yang <chih.chieh.yang@ibm.com>
```
  eaec4b91
13 Jul, 2024 1 commit

[ci] try to add multi-node tests (#6280) · 41708e50

youkaichao authored Jul 12, 2024


Signed-off-by: Muralidhar Andoorveedu <muralidhar.andoorveedu@centml.ai>
Co-authored-by: Muralidhar Andoorveedu <muralidhar.andoorveedu@centml.ai>

41708e50

10 Jul, 2024 3 commits
- [Bugfix][Neuron] Fix soft prompt method error in NeuronExecutor (#6313) · 997df46a
  Woosuk Kwon authored Jul 10, 2024
  
  997df46a
- [Bugfix] Fix OpenVINOExecutor abstractmethod error (#6296) · 44cc7661
  sangjune.park authored Jul 11, 2024
```
Signed-off-by: sangjune.park <sangjune.park@navercorp.com>
```
  44cc7661
- [Bugfix][TPU] Add prompt adapter methods to TPUExecutor (#6279) · 5ed3505d
  Woosuk Kwon authored Jul 09, 2024
  
  5ed3505d