Commits · 7a83b1aec06834e58174694042105e365828507a · OpenDAS / vllm_cscc · GitLab

05 Nov, 2024 4 commits
- [BugFix] Lazy import ray (#10021) · 7a83b1ae
  Gene Der Su authored Nov 05, 2024
  
  7a83b1ae
- [Bugfix] Fixup Mamba (#10004) · ad233189
  Tyler Michael Smith authored Nov 04, 2024
```
Signed-off-by: Tyler Michael Smith <tyler@neuralmagic.com>
```
  ad233189
- [Core] Make encoder-decoder inputs a nested structure to be more composable (#9604) · bbc3619d
  Cyrus Leung authored Nov 05, 2024
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  bbc3619d
- [Core] Use os.sched_yield in ShmRingBuffer instead of time.sleep (#9994) · 04bbf38e
  Tyler Michael Smith authored Nov 04, 2024
```
Signed-off-by: Tyler Michael Smith <tyler@neuralmagic.com>
```
  04bbf38e
04 Nov, 2024 14 commits
- [Bugfix] Respect modules_to_not_convert within awq_marlin (#9895) · 8f0a9ca8
  Michael Goin authored Nov 04, 2024
```
Signed-off-by: mgoin <michael@neuralmagic.com>
```
  8f0a9ca8
- [4.5/N] bugfix for quant config in speculative decode (#10007) · 2094062b
  youkaichao authored Nov 04, 2024
```
Signed-off-by: youkaichao <youkaichao@gmail.com>
```
  2094062b
- [Frontend] Add max_tokens prometheus metric (#9881) · ac04a97a
  tomeras91 authored Nov 05, 2024
```
Signed-off-by: Tomer Asida <tomera@ai21.com>
```
  ac04a97a
- [Bugfix] Fix `MQLLMEngine` hanging (#9973) · 04cef2c6
  Robert Shaw authored Nov 04, 2024
```
Signed-off-by: rshaw@neuralmagic.com <rshaw@neuralmagic.com>
```
  04cef2c6
- [Model] factoring out MambaMixer out of Jamba (#8993) · 603a661a
  Mor Zusman authored Nov 04, 2024
```
Signed-off-by: mzusman <mor.zusmann@gmail.com>
```
  603a661a
- [Misc]Reduce BNB static variable (#9987) · fb2716d6
  Jee Jee Li authored Nov 05, 2024
```
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
```
  fb2716d6
- [4/N] make quant config first-class citizen (#9978) · 8d72bb20
  youkaichao authored Nov 04, 2024
```
Signed-off-by: youkaichao <youkaichao@gmail.com>
```
  8d72bb20
- [Frontend] Multi-Modality Support for Loading Local Image Files (#9915) · ac6b8f19
  Chauncey authored Nov 04, 2024
```
Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>
```
  ac6b8f19
- [Bugfix][OpenVINO] Fix circular reference #9939 (#9974) · ccb5376a
  Mengqing Cao authored Nov 04, 2024
```
Signed-off-by: MengqingCao <cmq0113@163.com>
```
  ccb5376a
- [Misc] Compute query_start_loc/seq_start_loc on CPU (#9447) · 4dbcbbeb
  Yang Zheng authored Nov 04, 2024
```
Co-authored-by: Yang Zheng(SW)(Alex) <you@example.com>
```
  4dbcbbeb
- [Bugfix]Using the correct type hints (#9885) · b67feb12
  Gregory Shtrasberg authored Nov 04, 2024
```
Signed-off-by: Gregory Shtrasberg <Gregory.Shtrasberg@amd.com>
```
  b67feb12
- [Bugfix] Fix MiniCPMV and Mllama BNB bug (#9917) · c49f0407
  Jee Jee Li authored Nov 04, 2024
```
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
```
  c49f0407
- [V1] Fix Configs (#9971) · 91c9ebbb
  Robert Shaw authored Nov 03, 2024
  
  91c9ebbb
- [Model] Add support for H2OVL-Mississippi models (#9747) · 54597724
  shanshan wang authored Nov 03, 2024
```
Signed-off-by: Shanshan Wang <shanshan.wang@h2o.ai>
Signed-off-by: Roger Wang <ywang@roblox.com>
Co-authored-by: Roger Wang <ywang@roblox.com>
```
  54597724
03 Nov, 2024 1 commit
- [V1] Support per-request seed (#9945) · 1f1b6d6e
  Nick Hill authored Nov 03, 2024
```
Signed-off-by: Nick Hill <nickhill@us.ibm.com>
```
  1f1b6d6e
02 Nov, 2024 8 commits
- [bugfix] fix tsts (#9959) · 3bb4befe
  youkaichao authored Nov 02, 2024
```
Signed-off-by: youkaichao <youkaichao@gmail.com>
```
  3bb4befe
- [torch.compile] Adding torch compile to vision-language models (#9946) · ae5279a1
  Yongzao authored Nov 03, 2024
  
  ae5279a1
- [3/N] model runner pass the whole config to model (#9958) · cea808f3
  youkaichao authored Nov 02, 2024
```
Signed-off-by: youkaichao <youkaichao@gmail.com>
```
  cea808f3
- [bugfix] fix chatglm dummy_data_for_glmv (#9955) · 74b529ce
  youkaichao authored Nov 02, 2024
```
Signed-off-by: youkaichao <youkaichao@gmail.com>
```
  74b529ce
- [V1] Fix `EngineArgs` refactor on V1 (#9954) · d6459b45
  Robert Shaw authored Nov 02, 2024
  
  d6459b45
- [2/N] executor pass the complete config to worker/modelrunner (#9938) · e8937954
  youkaichao authored Nov 02, 2024
```
Signed-off-by: youkaichao <youkaichao@gmail.com>
Co-authored-by: Nick Hill <nhill@redhat.com>
```
  e8937954
- [torch.compile] fix cpu broken code (#9947) · af7380d8
  youkaichao authored Nov 01, 2024
```
Signed-off-by: youkaichao <youkaichao@gmail.com>
```
  af7380d8
- [Encoder Decoder] Add flash_attn kernel support for encoder-decoder models (#9559) · a78dd330
  sroy745 authored Nov 01, 2024
  
  a78dd330
01 Nov, 2024 13 commits
- [Core][VLM] Add precise multi-modal placeholder tracking (#8346) · 6c0b7f54
  Peter Salas authored Nov 01, 2024
```
Signed-off-by: Peter Salas <peter@fixie.ai>
```
  6c0b7f54
- [Bugfix] PicklingError on RayTaskError (#9934) · 27cd36e6
  Gene Der Su authored Nov 01, 2024
```
Signed-off-by: Gene Su <e870252314@gmail.com>
```
  27cd36e6
- [1/N] pass the complete config from engine to executor (#9933) · 18bd7587
  youkaichao authored Nov 01, 2024
```
Signed-off-by: youkaichao <youkaichao@gmail.com>
```
  18bd7587
- [Bugfix/Core] Flashinfer k_scale and v_scale (#9861) · 598b6d7b
  Pavani Majety authored Nov 01, 2024
  
  598b6d7b
- [torch.compile] use interpreter with stable api from pytorch (#9889) · aff1fd81
  youkaichao authored Nov 01, 2024
```
Signed-off-by: youkaichao <youkaichao@gmail.com>
```
  aff1fd81
- [Core] Refactor: Clean up unused argument in Scheduler._preempt (#9696) · 4581d2cc
  André Jonasson authored Nov 01, 2024
```
Signed-off-by: André Jonasson <andre.jonasson@gmail.com>
```
  4581d2cc
- [Bugfix] Fix edge cases for MistralTokenizer (#9625) · 1dd4cb29
  Travis Johnson authored Nov 01, 2024
```
Signed-off-by: Travis Johnson <tsjohnso@us.ibm.com>
Signed-off-by: Prashant Gupta <prashantgupta@us.ibm.com>
Co-authored-by: Prashant Gupta <prashantgupta@us.ibm.com>
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
```
  1dd4cb29
- [Frontend] Use a proper chat template for VLM2Vec (#9912) · ba0d8920
  Cyrus Leung authored Nov 01, 2024
  
  ba0d8920
- [Frontend] Chat-based Embeddings API (#9759) · 06386a64
  Cyrus Leung authored Nov 01, 2024
  
  06386a64
- [torch.compile] Adding torch compile annotations to some models (#9876) · 2b5bf209
  Yongzao authored Nov 01, 2024
```
Signed-off-by: youkaichao <youkaichao@gmail.com>
Co-authored-by: youkaichao <youkaichao@gmail.com>
```
  2b5bf209
- [Model] Support bitsandbytes for MiniCPMV (#9891) · 93a76dd2
  Michael Goin authored Nov 01, 2024
```
Signed-off-by: mgoin <michael@neuralmagic.com>
```
  93a76dd2
- [torch.compile] rework test plans (#9866) · 566cd277
  youkaichao authored Oct 31, 2024
```
Signed-off-by: youkaichao <youkaichao@gmail.com>
```
  566cd277
- [Bugfix] Fix layer skip logic with bitsandbytes (#9887) · 37a4947d
  Michael Goin authored Nov 01, 2024
```
Signed-off-by: mgoin <michael@neuralmagic.com>
```
  37a4947d