Commits · 50b8d08dbd4493327e344bc627a0613947deba8f · OpenDAS / vllm_cscc · GitLab

16 Aug, 2024 6 commits
- [Misc/Testing] Use `torch.testing.assert_close` (#7324) · 50b8d08d
  jon-chuang authored Aug 15, 2024
  
  50b8d08d
- [CI] Move quantization cpu offload tests out of fastcheck (#7574) · e1655287
  Michael Goin authored Aug 16, 2024
  
  e1655287
- Chat method for offline llm (#5049) · 3b19e39d
  nunjunj authored Aug 16, 2024
```
Co-authored-by: nunjunj <ray@g-3ff9f30f2ed650001.c.vllm-405802.internal>
Co-authored-by: nunjunj <ray@g-1df6075697c3f0001.c.vllm-405802.internal>
Co-authored-by: nunjunj <ray@g-c5a2c23abc49e0001.c.vllm-405802.internal>
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
Co-authored-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  3b19e39d
- [ci/test] rearrange tests and make adag test soft fail (#7572) · 4cd7d47f
  youkaichao authored Aug 15, 2024
  
  4cd7d47f
- [Feature]: Add OpenAI server prompt_logprobs support #6508 (#7453) · f878c8fe
  Grant Pinkert authored Aug 16, 2024
  
  f878c8fe
- [Misc] Add quantization config support for speculative model. (#7343) · b67ae00c
  shangmingc authored Aug 16, 2024
  
  b67ae00c
14 Aug, 2024 5 commits
- [Misc] Revert `compressed-tensors` code reuse (#7521) · f55a9aea
  Kyle Sayers authored Aug 14, 2024
  
  f55a9aea
- [VLM][Core] Support profiling with multiple multi-modal inputs per prompt (#7126) · 3f674a49
  Cyrus Leung authored Aug 15, 2024
  
  3f674a49
- [Misc] Deprecation Warning when setting --engine-use-ray (#7424) · 70b746ef
  Wallas Henrique authored Aug 14, 2024
```
Signed-off-by: Wallas Santos <wallashss@ibm.com>
Co-authored-by: youkaichao <youkaichao@gmail.com>
Co-authored-by: Nick Hill <nickhill@us.ibm.com>
Co-authored-by: youkaichao <youkaichao@126.com>
```
  70b746ef
- [misc][ci] fix cpu test with plugins (#7489) · ea49e6a3
  youkaichao authored Aug 13, 2024
  
  ea49e6a3
- [CI/Build]Reduce the time consumption for LoRA tests (#7396) · 97992802
  Jee Jee Li authored Aug 14, 2024
  
  97992802
13 Aug, 2024 10 commits
- [misc][plugin] add plugin system implementation (#7426) · 16422ea7
  youkaichao authored Aug 13, 2024
  
  16422ea7
- [Misc] `compressed-tensors` code reuse (#7277) · 373538f9
  Kyle Sayers authored Aug 13, 2024
  
  373538f9
- [frontend] spawn engine process from api server process (#7484) · 33e5d7e6
  youkaichao authored Aug 13, 2024
  
  33e5d7e6
- [Misc] Update `awq` and `awq_marlin` to use `vLLMParameters` (#7422) · b1e5afc3
  Dipika Sikka authored Aug 13, 2024
  
  b1e5afc3
- [Misc] Update `gptq_marlin` to use new vLLMParameters (#7281) · fb377d7e
  Dipika Sikka authored Aug 13, 2024
  
  fb377d7e
- [Frontend][Core] Add plumbing to support audio language models (#7446) · 00c3d68e
  Peter Salas authored Aug 13, 2024
  
  00c3d68e
- [Bugfix] Fix weight loading for Chameleon when TP>1 (#7410) · 7025b11d
  Cyrus Leung authored Aug 13, 2024
  
  7025b11d
- [Misc] improve logits processors logging message (#7435) · 97a6be95
  Andrew Wang authored Aug 12, 2024
  
  97a6be95
- [mypy] Misc. typing improvements (#7417) · 9ba85bc1
  Cyrus Leung authored Aug 13, 2024
  
  9ba85bc1
- [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 2 commits
- [Core/Bugfix] Add FP8 K/V Scale and dtype conversion for prefix/prefill Triton Kernel (#7208) · a046f863
  jon-chuang authored Aug 12, 2024
```
Co-authored-by: Cody Yu <hao.yu.cody@gmail.com>
```
  a046f863
- [Core][VLM] Support image embeddings as input (#6613) · e6e42e4b
  Roger Wang authored Aug 12, 2024
  
  e6e42e4b
10 Aug, 2024 1 commit
- [Bugfix] Fix phi3v batch inference when images have different aspect ratio (#7392) · 4c5d8e8e
  Isotr0py authored Aug 11, 2024
  
  4c5d8e8e
09 Aug, 2024 7 commits
- [Core] Fix edge case in chunked prefill + block manager v2 (#7380) · baa24025
  Cade Daniel authored Aug 09, 2024
  
  baa24025
- [Core] Add span metrics for model_forward, scheduler and sampler time (#7089) · 933790c2
  Mahesh Keralapura authored Aug 09, 2024
  
  933790c2
- [Frontend] Support embeddings in the run_batch API (#7132) · 249b8822
  Pooya Davoodi authored Aug 09, 2024
```
Co-authored-by: Simon Mo <simon.mo@hey.com>
```
  249b8822
- [Core] Streamline stream termination in `AsyncLLMEngine` (#7336) · b4e9528f
  Nick Hill authored Aug 09, 2024
  
  b4e9528f
- [Speculative decoding] [Multi-Step] decouple should_modify_greedy_probs_inplace (#6971) · 57b7be0e
  William Lin authored Aug 08, 2024
  
  57b7be0e
- [Bugfix] Fix speculative decoding with MLPSpeculator with padded vocabulary (#7218) · 99b4cf5f
  Travis Johnson authored Aug 08, 2024
```
Signed-off-by: Travis Johnson <tsjohnso@us.ibm.com>
```
  99b4cf5f
- [Core] Support serving encoder/decoder models (#7258) · 7eb4a51c
  Cyrus Leung authored Aug 09, 2024
  
  7eb4a51c
08 Aug, 2024 3 commits
- [Bugfix][fast] Fix the get_num_blocks_touched logic (#6849) · 782e53ab
  Zach Zheng authored Aug 08, 2024
  
  782e53ab
- [Frontend] Kill the server on engine death (#6594) · 21b9c49a
  Joe Runde authored Aug 08, 2024
```
Signed-off-by: Joe Runde <joe@joerun.de>
Signed-off-by: Joe Runde <Joseph.Runde@ibm.com>
```
  21b9c49a
- [Bugfix][Kernel] Increased atol to fix failing tests (#7305) · 5fb4a3f6
  Luka Govedič authored Aug 08, 2024
  
  5fb4a3f6
07 Aug, 2024 6 commits
- [Bugfix][FP8] Fix dynamic FP8 Marlin quantization (#7219) · 5223199e
  Michael Goin authored Aug 07, 2024
  
  5223199e
- [BugFix] Fix frontend multiprocessing hang (#7217) · fde47d3b
  Maximilien de Bayser authored Aug 07, 2024
```
Signed-off-by: Max de Bayser <mbayser@br.ibm.com>
Co-authored-by: Robert Shaw <114415538+robertgshaw2-neuralmagic@users.noreply.github.com>
```
  fde47d3b
- [Bugfix] Fix input processor for InternVL2 model (#7164) · b7645476
  Isotr0py authored Aug 08, 2024
```
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
```
  b7645476
- [Misc] Refactor linear layer weight loading; introduce `BasevLLMParameter` and... · 0f7052bc
  Dipika Sikka authored Aug 07, 2024
```
[Misc] Refactor linear layer weight loading; introduce `BasevLLMParameter` and `weight_loader_v2` (#5874)
```
  0f7052bc
- [Frontend] Gracefully handle missing chat template and fix CI failure (#7238) · 66d617e3
  Cyrus Leung authored Aug 07, 2024
```
Co-authored-by: Roger Wang <ywang@roblox.com>
```
  66d617e3
- [BugFix] Overhaul async request cancellation (#7111) · 9a3f49ae
  Nick Hill authored Aug 06, 2024
  
  9a3f49ae