Commits · 82079729ccd0830ce77fcc5fd7ea2be3bf81ccaf · OpenDAS / vllm_cscc · GitLab

26 Jun, 2024 1 commit
- [Bugfix] Fix assertion in NeuronExecutor (#5841) · 82079729
  aws-patlange authored Jun 25, 2024
  
  82079729
25 Jun, 2024 2 commits
- [Hardware][AMD][CI/Build][Doc] Upgrade to ROCm 6.1, Dockerfile improvements, test fixes (#5422) · dd793d1d
  Matt Wong authored Jun 25, 2024
  
  dd793d1d
- [Hardware][TPU] Refactor TPU backend (#5831) · bc34937d
  Woosuk Kwon authored Jun 25, 2024
  
  bc34937d
22 Jun, 2024 1 commit
- [Bugfix] Fix pin_lora error in TPU executor (#5760) · 0cbc1d2b
  Woosuk Kwon authored Jun 21, 2024
  
  0cbc1d2b
21 Jun, 2024 1 commit
- [LoRA] Add support for pinning lora adapters in the LRU cache (#5603) · f5dda63e
  rohithkrn authored Jun 21, 2024
  
  f5dda63e
19 Jun, 2024 1 commit
- [misc][distributed] use 127.0.0.1 for single-node (#5619) · 3eea7488
  youkaichao authored Jun 19, 2024
  
  3eea7488
17 Jun, 2024 2 commits
- [bugfix][distributed] fix 16 gpus local rank arrangement (#5604) · 1b44aaf4
  youkaichao authored Jun 17, 2024
  
  1b44aaf4
- [Hardware][Intel GPU] Add Intel GPU(XPU) inference backend (#3814) · 728c4c8a
  Kunshang Ji authored Jun 18, 2024
```
Co-authored-by: Jiang Li <jiang1.li@intel.com>
Co-authored-by: Abhilash Majumder <abhilash.majumder@intel.com>
Co-authored-by: Abhilash Majumder <30946547+abhilash1910@users.noreply.github.com>
```
  728c4c8a
13 Jun, 2024 1 commit
- Add `cuda_device_count_stateless` (#5473) · 50eed24d
  Antoni Baum authored Jun 13, 2024
  
  50eed24d
12 Jun, 2024 1 commit
- [Hardware] Initial TPU integration (#5292) · 1a8bfd92
  Woosuk Kwon authored Jun 12, 2024
  
  1a8bfd92
11 Jun, 2024 2 commits
- [Core][Doc] Default to multiprocessing for single-node distributed case (#5230) · 99dac099
  Nick Hill authored Jun 11, 2024
```
Co-authored-by: Antoni Baum <antoni.baum@protonmail.com>
```
  99dac099
- [Bugfix] Fix `MultiprocessingGPUExecutor.check_health` when world_size == 1 (#5254) · 2e02311a
  Junichi Sato authored Jun 12, 2024
  
  2e02311a
07 Jun, 2024 1 commit
- Remove Ray health check (#4693) · 18a277b5
  Antoni Baum authored Jun 07, 2024
  
  18a277b5
04 Jun, 2024 1 commit
- [Bugfix] Fix torch.compile() error when using MultiprocessingGPUExecutor (#5229) · a58f24e5
  zifeitong authored Jun 03, 2024
  
  a58f24e5
22 May, 2024 1 commit
- [Core] Eliminate parallel worker per-step task scheduling overhead (#4894) · eb6d3c26
  Nick Hill authored May 22, 2024
  
  eb6d3c26
16 May, 2024 2 commits
- [Speculative decoding][Re-take] Enable TP>1 speculative decoding (#4840) · 973617ae
  Cody Yu authored May 16, 2024
```
Co-authored-by: Cade Daniel <edacih@gmail.com>
Co-authored-by: Cade Daniel <cade@anyscale.com>
```
  973617ae
- [Core] Implement sharded state loader (#4690) · 30e75439
  Aurick Qiao authored May 16, 2024
```
Co-authored-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
```
  30e75439
14 May, 2024 1 commit
- [Core] Add MultiprocessingGPUExecutor (#4539) · 676a9998
  Nick Hill authored May 14, 2024
```
Co-authored-by: SAHIL SUNEJA <suneja@us.ibm.com>
```
  676a9998
11 May, 2024 1 commit
- [Model][Misc] Add e5-mistral-7b-instruct and Embedding API (#3734) · e254497b
  Chang Su authored May 11, 2024
  
  e254497b
08 May, 2024 1 commit
- [Dynamic Spec Decoding] Auto-disable by the running queue size (#4592) · f942efb5
  Cody Yu authored May 08, 2024
```
Co-authored-by: Cade Daniel <edacih@gmail.com>
```
  f942efb5
07 May, 2024 1 commit

[Bug fix][Core] fixup ngram not setup correctly (#4551) · 8344f774

leiwen83 authored May 08, 2024


Co-authored-by: Lei Wen <wenlei03@qiyi.com>
Co-authored-by: Cade Daniel <edacih@gmail.com>
Co-authored-by: Cody Yu <hao.yu.cody@gmail.com>

8344f774

04 May, 2024 1 commit
- [Misc][Refactor] Introduce ExecuteModelData (#4540) · bc8ad684
  Cody Yu authored May 03, 2024
  
  bc8ad684
02 May, 2024 1 commit
- [Misc] centralize all usage of environment variables (#4548) · 5b8a7c1c
  youkaichao authored May 02, 2024
  
  5b8a7c1c
01 May, 2024 3 commits
- [Core] Add `multiproc_worker_utils` for multiprocessing-based workers (#4357) · a657bfc4
  Nick Hill authored May 01, 2024
  
  a657bfc4
- [Speculative decoding] Add ngram prompt lookup decoding (#4237) · b38e42fb
  leiwen83 authored May 02, 2024
```
Co-authored-by: Lei Wen <wenlei03@qiyi.com>
```
  b38e42fb
- [Core] Centralize GPU Worker construction (#4419) · 2e240c69
  Nick Hill authored Apr 30, 2024
  
  2e240c69
30 Apr, 2024 1 commit
- [BugFix] fix num_lookahead_slots missing in async executor (#4165) · 4bb53e2d
  leiwen83 authored May 01, 2024
```
Co-authored-by: Lei Wen <wenlei03@qiyi.com>
```
  4bb53e2d
27 Apr, 2024 2 commits
- [BugFix] Fix return type of executor execute_model methods (#4402) · ba4be44c
  Nick Hill authored Apr 27, 2024
  
  ba4be44c
- [Core] Introduce `DistributedGPUExecutor` abstract class (#4348) · 258a2c58
  Nick Hill authored Apr 26, 2024
  
  258a2c58
26 Apr, 2024 1 commit
- [CI] Disable non-lazy string operation on logging (#4326) · a88081bf
  SangBin Cho authored Apr 26, 2024
```
Co-authored-by: Danny Guinther <dguinther@neuralmagic.com>
```
  a88081bf
25 Apr, 2024 2 commits
- [Core] Add `shutdown()` method to `ExecutorBase` (#4349) · 15e7c675
  Nick Hill authored Apr 25, 2024
  
  15e7c675
- [Core] Move ray_utils.py from `engine` to `executor` package (#4347) · 479d69fa
  Nick Hill authored Apr 24, 2024
  
  479d69fa
23 Apr, 2024 3 commits
- [Bugfix] Add init_cached_hf_modules to RayWorkerWrapper (#4286) · d87f39e9
  DefTruth authored Apr 24, 2024
  
  d87f39e9
- [Speculative decoding 7/9] Speculative decoding end-to-end correctness tests. (#3951) · 62b8aebc
  Cade Daniel authored Apr 23, 2024
  
  62b8aebc
- [Core] Some simplification of WorkerWrapper changes (#4183) · 8f2ea22b
  Nick Hill authored Apr 23, 2024
  
  8f2ea22b
22 Apr, 2024 2 commits
- [Frontend] Enable support for CPU backend in AsyncLLMEngine. (#3993) · 077f0a2e
  Tao He authored Apr 22, 2024
```
Signed-off-by: Tao He <sighingnow@gmail.com>
```
  077f0a2e
- [Misc] Add vision language model support to CPU backend (#3968) · 296cdf8a
  Isotr0py authored Apr 22, 2024
  
  296cdf8a
18 Apr, 2024 2 commits
- [Core] add an option to log every function call to for debugging hang/crash in... · 8a7a3e44
  youkaichao authored Apr 18, 2024
```
[Core] add an option to log every function call to for debugging hang/crash in distributed inference (#4079)
Co-authored-by: Simon Mo <simon.mo@hey.com>
```
  8a7a3e44
- [CI/CD] add neuron docker and ci test scripts (#3571) · cd2f63fb
  Liangfu Chen authored Apr 18, 2024
  
  cd2f63fb
17 Apr, 2024 1 commit
- [Core] RayWorkerVllm --> WorkerWrapper to reduce duplication (#4024) · 8438e056
  youkaichao authored Apr 17, 2024
```
[Core] replace narrow-usage RayWorkerVllm to general WorkerWrapper to reduce code duplication (#4024)
```
  8438e056