Commits · 1e7d5c01f5c35424eede1bbe6f723dd8781120f0 · OpenDAS / vllm_cscc

"tests/entrypoints/pooling/openai/test_rerank.py" did not exist on "799397ee4f57b90ee1b5f12f88b12f4de0de0d1d"

24 Sep, 2024 13 commits
- [misc] soft drop beam search (#8763) · 1e7d5c01
  youkaichao authored Sep 24, 2024
  
  1e7d5c01
- [CI/Build] fix setuptools-scm usage (#8771) · 2467b642
  Daniele authored Sep 24, 2024
  
  2467b642
- [Bugfix] Fix torch dynamo fixes caused by `replace_parameters` (#8748) · 72fc97a0
  Lucas Wilkinson authored Sep 24, 2024
  
  72fc97a0
- [Frontend] Batch inference for llm.chat() API (#8648) · 2529d09b
  Andy authored Sep 24, 2024
```
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
Co-authored-by: Roger Wang <ywang@roblox.com>
Co-authored-by: Roger Wang <136131678+ywang96@users.noreply.github.com>
```
  2529d09b
- [Kernel] Split Marlin MoE kernels into multiple files (#8661) · a928ded9
  ElizaWszola authored Sep 24, 2024
```
Co-authored-by: mgoin <michael@neuralmagic.com>
```
  a928ded9
- [Bugfix] Fix potentially unsafe custom allreduce synchronization (#8558) · cc4325b6
  Hanzhi Zhou authored Sep 24, 2024
  
  cc4325b6
- [Model] Expose Phi3v num_crops as a mm_processor_kwarg (#8658) · 8ff7ced9
  Alex Brooks authored Sep 24, 2024
```
Signed-off-by: Alex-Brooks <Alex.Brooks@ibm.com>
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
Co-authored-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  8ff7ced9
- [Core][Model] Support loading weights by ID within models (#7931) · 3f06bae9
  Peter Salas authored Sep 24, 2024
  
  3f06bae9
- [MISC] Skip dumping inputs when unpicklable (#8744) · b8747e8a
  Cody Yu authored Sep 23, 2024
  
  b8747e8a
- Revert "[Core] Rename `PromptInputs` to `PromptType`, and `inputs` to `prompt`" (#8750) · 3185fb0c
  Simon Mo authored Sep 23, 2024
  
  3185fb0c
- re-implement beam search on top of vllm core (#8726) · 0250dd68
  youkaichao authored Sep 23, 2024
```
Co-authored-by: Brendan Wong <bjwpokemon@gmail.com>
```
  0250dd68
- Fix tests in test_scheduler.py that fail with BlockManager V2 (#8728) · 88577ac9
  sroy745 authored Sep 23, 2024
  
  88577ac9
- [Hardware][AMD] ROCm6.2 upgrade (#8674) · 530821d0
  Hongxia Yang authored Sep 23, 2024
  
  530821d0
23 Sep, 2024 14 commits
- Add output streaming support to multi-step + async while ensuring RequestOutput obj reuse (#8335) · 1a2aef3e
  Alexander Matveev authored Sep 23, 2024
  
  1a2aef3e
- Fix typical acceptance sampler with correct recovered token ids (#8562) · 5f7bb584
  jiqing-feng authored Sep 24, 2024
  
  5f7bb584
- [Core] Allow IPv6 in VLLM_HOST_IP with zmq (#8575) · b05f5c92
  Russell Bryant authored Sep 23, 2024
```
Signed-off-by: Russell Bryant <rbryant@redhat.com>
```
  b05f5c92
- [Kernel][LoRA] Add assertion for punica sgmv kernels (#7585) · 9b0e3ec9
  Jee Jee Li authored Sep 24, 2024
  
  9b0e3ec9
- [Kernel] (2/N) Machete - Integrate into CompressedTensorsWNA16 and GPTQMarlin (#7701) · 86e9c8df
  Lucas Wilkinson authored Sep 23, 2024
```
Co-authored-by: mgoin <michael@neuralmagic.com>
Co-authored-by: Divakar Verma <137818590+divakar-amd@users.noreply.github.com>
Co-authored-by: Tyler Michael Smith <tyler@neuralmagic.com>
```
  86e9c8df
- [CI/Build] use setuptools-scm to set __version__ (#4738) · ee5f34b1
  Daniele authored Sep 23, 2024
```
Co-authored-by: youkaichao <youkaichao@126.com>
```
  ee5f34b1
- [VLM] Fix paligemma, fuyu and persimmon with transformers 4.45 : use... · f2bd246c
  Jani Monoses authored Sep 23, 2024
```
[VLM] Fix paligemma, fuyu and persimmon with transformers 4.45 : use config.text_config.vocab_size (#8707)
```
  f2bd246c
- [Model] Support pp for qwen2-vl (#8696) · a79e5229
  Yanyi Liu authored Sep 23, 2024
  
  a79e5229
- [Bugfix][CPU] fix missing input intermediate_tensors in the cpu_model_runner (#8733) · 3e83c12b
  Li, Jiang authored Sep 23, 2024
  
  3e83c12b
- [Hardware][CPU] Refactor CPU model runner (#8729) · e551ca15
  Isotr0py authored Sep 23, 2024
  
  e551ca15
- [Core][Frontend] Support Passing Multimodal Processor Kwargs (#8657) · 9b8c8ba1
  Alex Brooks authored Sep 23, 2024
```
Signed-off-by: Alex-Brooks <Alex.Brooks@ibm.com>
```
  9b8c8ba1
- [Bugfix] fix docker build for xpu (#8652) · d23679eb
  Yan Ma authored Sep 23, 2024
  
  d23679eb
- [Bugfix] Fix CPU CMake build (#8723) · 57a0702e
  Luka Govedič authored Sep 22, 2024
```
Co-authored-by: Yuan <yuan.zhou@intel.com>
```
  57a0702e
- [Bugfix] Avoid some bogus messages RE CUTLASS's revision when building (#8702) · 3dda7c22
  Tyler Michael Smith authored Sep 22, 2024
  
  3dda7c22
22 Sep, 2024 9 commits
- [misc] upgrade mistral-common (#8715) · 92ba7e74
  youkaichao authored Sep 22, 2024
  
  92ba7e74
- [build] enable existing pytorch (for GH200, aarch64, nightly) (#8713) · d4a2ac83
  youkaichao authored Sep 22, 2024
  
  d4a2ac83
- [SpecDec][Misc] Cleanup, remove bonus token logic. (#8701) · c6bd70d7
  Lily Liu authored Sep 22, 2024
  
  c6bd70d7
- [Model][VLM] Add LLaVA-Onevision model support (#8486) · 5b595327
  litianjian authored Sep 23, 2024
```
Co-authored-by: litianjian <litianjian@bytedance.com>
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
Co-authored-by: Roger Wang <ywang@roblox.com>
Co-authored-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  5b595327
- [MISC] rename CudaMemoryProfiler to DeviceMemoryProfiler (#8703) · ca2b628b
  Huazhong Ji authored Sep 23, 2024
  
  ca2b628b
- [Misc] Use NamedTuple in Multi-image example (#8705) · 8ca5051b
  Alex Brooks authored Sep 22, 2024
```
Signed-off-by: Alex-Brooks <Alex.Brooks@ibm.com>
```
  8ca5051b
- [Model] Refactor BLIP/BLIP-2 to support composite model loading (#8407) · 06ed2815
  Cyrus Leung authored Sep 22, 2024
  
  06ed2815
- [ci][build] fix vllm-flash-attn (#8699) · 0e40ac9b
  youkaichao authored Sep 21, 2024
  
  0e40ac9b
- [Bugfix] Refactor composite weight loading logic (#8656) · 13d88d41
  Isotr0py authored Sep 22, 2024
  
  13d88d41
21 Sep, 2024 4 commits
- [Kernel][Bugfix] Delete some more useless code in marlin_moe_ops.cu (#8643) · d66ac628
  Tyler Michael Smith authored Sep 21, 2024
  
  d66ac628
- [dbrx] refactor dbrx experts to extend FusedMoe class (#8518) · 9dc7c6c7
  Divakar Verma authored Sep 21, 2024
  
  9dc7c6c7
- [Kernel][Triton][AMD] Remove tl.atomic_add from awq_gemm_kernel, 2-5x speedup... · ec4aaad8
  rasmith authored Sep 21, 2024
```
[Kernel][Triton][AMD] Remove tl.atomic_add from awq_gemm_kernel, 2-5x speedup MI300, minor improvement for MI250 (#8646)
```
  ec4aaad8
- [Doc] Fix typo in AMD installation guide (#8689) · 4dfdf431
  Andy Dai authored Sep 21, 2024
  
  4dfdf431