Commits · 1f26efbb3a5e6dad0b98421dd697167c42a50629 · OpenDAS / vllm_cscc · GitLab

06 Aug, 2024 3 commits
- [Model] Support SigLIP encoder and alternative decoders for LLaVA models (#7153) · 1f26efbb
  Cyrus Leung authored Aug 06, 2024
```
Co-authored-by: Roger Wang <136131678+ywang96@users.noreply.github.com>
```
  1f26efbb
- [LoRA] Relax LoRA condition (#7146) · 9118217f
  Jee Jee Li authored Aug 06, 2024
  
  9118217f
- [Build] Add initial conditional testing spec (#6841) · e3c664bf
  Simon Mo authored Aug 05, 2024
  
  e3c664bf
05 Aug, 2024 17 commits
- [Core] Support loading GGUF model (#5191) · 360bd67c
  Isotr0py authored Aug 06, 2024
```
Co-authored-by: Michael Goin <michael@neuralmagic.com>
```
  360bd67c
- [MISC] Use non-blocking transfer in prepare_input (#7172) · ef527be0
  Cody Yu authored Aug 05, 2024
  
  ef527be0
- [Bugfix] Specify device when loading LoRA and embedding tensors (#7129) · 89b8db6b
  Jacob Schein authored Aug 05, 2024
```
Co-authored-by: Jacob Schein <jacobschein@Jacobs-MacBook-Pro-2.local>
```
  89b8db6b
- [Doc] [SpecDecode] Update MLPSpeculator documentation (#7100) · 789937af
  Thomas Parnell authored Aug 06, 2024
```
Signed-off-by: Thomas Parnell <tpa@zurich.ibm.com>
```
  789937af
- [ci][frontend] deduplicate tests (#7101) · dfb1a15d
  youkaichao authored Aug 05, 2024
  
  dfb1a15d
- bump version to v0.5.4 (#7139) · 4db5176d
  Simon Mo authored Aug 05, 2024
  
  4db5176d
- [Bugfix][CI/Build] Fix CUTLASS FetchContent (#7171) · 4cf1dc39
  Tyler Michael Smith authored Aug 05, 2024
  
  4cf1dc39
- [CI/Build] Suppress divide-by-zero and missing return statement warnings (#7001) · 6e4852ce
  Tyler Michael Smith authored Aug 05, 2024
  
  6e4852ce
- [Kernel] Update CUTLASS to 3.5.1 (#7085) · 8571ac46
  Tyler Michael Smith authored Aug 05, 2024
  
  8571ac46
- [Misc] Fix typo in GroupCoordinator.recv() (#7167) · 997cf783
  Rui Qiao authored Aug 05, 2024
```
Signed-off-by: Rui Qiao <ruisearch42@gmail.com>
```
  997cf783
- [BugFix] Use args.trust_remote_code (#7121) · 57f560aa
  Aditya Paliwal authored Aug 05, 2024
  
  57f560aa
- [BugFix] Use IP4 localhost form for zmq bind (#7163) · 003f8ee1
  Nick Hill authored Aug 05, 2024
  
  003f8ee1
- [SpecDecode] Support FlashInfer in DraftModelRunner (#6926) · e9630458
  Bongwon Jang authored Aug 06, 2024
  
  e9630458
- [Speculative decoding] Add periodic log with time spent in proposal/scoring/verification (#6963) · 82a1b1a8
  Cade Daniel authored Aug 05, 2024
  
  82a1b1a8
- [Model] SiglipVisionModel ported from transformers (#6942) · c0d8f163
  Jungho Christopher Cho authored Aug 05, 2024
```
Co-authored-by: Roger Wang <ywang@roblox.com>
```
  c0d8f163
- [Frontend] Reapply "Factor out code for running uvicorn" (#7095) · cc08fc72
  Cyrus Leung authored Aug 05, 2024
  
  cc08fc72
- [Model] Add multi-image support for minicpmv (#7122) · 7b86e7c9
  Alphi authored Aug 05, 2024
```
Co-authored-by: hezhihui <hzh7269@modelbest.cn>
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
```
  7b86e7c9
04 Aug, 2024 7 commits
- Clean up remaining Punica C information (#7027) · f80ab352
  Jee Jee Li authored Aug 05, 2024
  
  f80ab352
- [misc][distributed] improve libcudart.so finding (#7127) · 16a1cc9b
  youkaichao authored Aug 04, 2024
  
  16a1cc9b
- [Bugfix] [SpecDecode] Default speculative_draft_tensor_parallel_size to 1 when... · b1c9aa3d
  Thomas Parnell authored Aug 04, 2024
```
[Bugfix] [SpecDecode] Default speculative_draft_tensor_parallel_size to 1 when using MLPSpeculator (#7105)
Signed-off-by: Thomas Parnell <tpa@zurich.ibm.com>
```
  b1c9aa3d
- [Model]Refactor MiniCPMV (#7020) · 179a6a36
  Jee Jee Li authored Aug 04, 2024
```
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
```
  179a6a36
- [core][misc] simply output processing with shortcut code path (#7117) · 83c644fe
  youkaichao authored Aug 04, 2024
  
  83c644fe
- [misc] add zmq in collect env (#7119) · 9fadc7b7
  youkaichao authored Aug 03, 2024
  
  9fadc7b7
- Support for guided decoding for offline LLM (#6878) · 654bc5ca
  Yihuan Bu authored Aug 03, 2024
```
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
```
  654bc5ca
03 Aug, 2024 11 commits
- [Frontend] Warn if user `max_model_len` is greater than derived `max_model_len` (#7080) · 825b0448
  Jeff Fialho authored Aug 03, 2024
```
Signed-off-by: Jefferson Fialho <jfialho@ibm.com>
Co-authored-by: Nick Hill <nickhill@us.ibm.com>
```
  825b0448
- [ci][test] finalize fork_new_process_for_each_test (#7114) · 44dcb52e
  youkaichao authored Aug 03, 2024
  
  44dcb52e
- [CI] Temporarily turn off H100 performance benchmark (#7104) · 67d745cc
  Kuntai Du authored Aug 02, 2024
  
  67d745cc
- [LoRA] ReplicatedLinear support LoRA (#7081) · 99d7cabd
  Jee Jee Li authored Aug 03, 2024
  
  99d7cabd
- [Bugfix] Fix block table for seqs that have prefix cache hits (#7018) · fb2c1c86
  Zach Zheng authored Aug 02, 2024
  
  fb2c1c86
- [Model] Refactor and decouple weight loading logic for InternVL2 model (#7067) · 0c25435d
  Isotr0py authored Aug 03, 2024
  
  0c25435d
- [ci][distributed] disable ray dag tests (#7099) · a0d16456
  youkaichao authored Aug 02, 2024
  
  a0d16456
- [ci][distributed] merge distributed test commands (#7097) · 04e55834
  youkaichao authored Aug 02, 2024
```
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
```
  04e55834
- [Frontend] Factor out chat message parsing (#7055) · 8c025fa7
  Cyrus Leung authored Aug 03, 2024
  
  8c025fa7
- [ci][distributed] shorten wait time if server hangs (#7098) · 69ea15e5
  youkaichao authored Aug 02, 2024
  
  69ea15e5
- [ Frontend ] Multiprocessing for OpenAI Server with `zeromq` (#6883) · ed812a73
  Robert Shaw authored Aug 02, 2024
```
Signed-off-by: Joe Runde <Joseph.Runde@ibm.com>
Co-authored-by: Joe Runde <Joseph.Runde@ibm.com>
Co-authored-by: Joe Runde <joe@joerun.de>
Co-authored-by: Nick Hill <nickhill@us.ibm.com>
Co-authored-by: Simon Mo <simon.mo@hey.com>
```
  ed812a73
02 Aug, 2024 2 commits
- [misc] add a flag to enable compile (#7092) · 70898934
  youkaichao authored Aug 02, 2024
  
  70898934
- [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