Commits · d9cd78eb718c233ebc5b84377fc2226af7ef0fa2 · OpenDAS / vllm_cscc · GitLab

18 Sep, 2024 3 commits
- [BugFix] Nonzero exit code if MQLLMEngine startup fails (#8572) · d9cd78eb
  Nick Hill authored Sep 18, 2024
  
  d9cd78eb
- [Core][Bugfix][Perf] Introduce `MQLLMEngine` to avoid `asyncio` OH (#8157) · 7c7714d8
  Alexander Matveev authored Sep 18, 2024
```
Co-authored-by: Nick Hill <nickhill@us.ibm.com>
Co-authored-by: rshaw@neuralmagic.com <rshaw@neuralmagic.com>
Co-authored-by: Robert Shaw <114415538+robertgshaw2-neuralmagic@users.noreply.github.com>
Co-authored-by: Simon Mo <simon.mo@hey.com>
```
  7c7714d8
- [Misc] Add argument to disable FastAPI docs (#8554) · e3515729
  Jiaxin Shan authored Sep 18, 2024
  
  e3515729
17 Sep, 2024 1 commit
- [Model] Add mistral function calling format to all models loaded with "mistral" format (#8515) · a54ed802
  Patrick von Platen authored Sep 17, 2024
```
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
```
  a54ed802
16 Sep, 2024 3 commits
- [Bugfix] Bind api server port before starting engine (#8491) · 47f5e03b
  Kevin Lin authored Sep 16, 2024
  
  47f5e03b
- [BugFix] Fix clean shutdown issues (#8492) · acd5511b
  Nick Hill authored Sep 16, 2024
  
  acd5511b
- [Frontend] Expose revision arg in OpenAI server (#8501) · 837c1968
  lewtun authored Sep 16, 2024
  
  837c1968
12 Sep, 2024 4 commits
- [Core] Add engine option to return only deltas or final output (#7381) · 551ce010
  Nick Hill authored Sep 12, 2024
  
  551ce010
- [BugFix] Fix Duplicate Assignment in Hermes2ProToolParser (#8423) · 1f0c75af
  Luis Vega authored Sep 12, 2024
  
  1f0c75af
- [Bugfix]: Fix the logic for deciding if tool parsing is used (#8366) · 5a60699c
  tomeras91 authored Sep 12, 2024
  
  5a60699c
- [misc] remove engine_use_ray (#8126) · f842a7af
  youkaichao authored Sep 11, 2024
  
  f842a7af
11 Sep, 2024 1 commit
- [Frontend] Create ErrorResponse instead of raising exceptions in run_batch (#8347) · cea95dfb
  Pooya Davoodi authored Sep 10, 2024
  
  cea95dfb
10 Sep, 2024 1 commit
- [Frontend] Clean up type annotations for mistral tokenizer (#8314) · 8c054b7a
  Cyrus Leung authored Sep 11, 2024
  
  8c054b7a
09 Sep, 2024 2 commits
- [Frontend] Add progress reporting to run_batch.py (#8060) · 58fcc854
  Adam Lugowski authored Sep 09, 2024
```
Co-authored-by: Adam Lugowski <adam.lugowski@parasail.io>
```
  58fcc854
- [Bugfix] Streamed tool calls now more strictly follow OpenAI's format; ensures... · 08287ef6
  Kyle Mistele authored Sep 09, 2024
```
[Bugfix] Streamed tool calls now more strictly follow OpenAI's format; ensures Vercel AI SDK compatibility (#8272)
```
  08287ef6
06 Sep, 2024 1 commit
- [Core] Support load and unload LoRA in api server (#6566) · db3bf7c9
  Jiaxin Shan authored Sep 05, 2024
```
Co-authored-by: Jee Jee Li <pandaleefree@gmail.com>
```
  db3bf7c9
04 Sep, 2024 3 commits
- [Feature] OpenAI-Compatible Tools API + Streaming for Hermes & Mistral models (#5649) · e02ce498
  Kyle Mistele authored Sep 04, 2024
```
Co-authored-by: constellate <constellate@1-ai-appserver-staging.codereach.com>
Co-authored-by: Kyle Mistele <kyle@constellate.ai>
```
  e02ce498
- [Frontend] Multimodal support in offline chat (#8098) · 855c262a
  Cyrus Leung authored Sep 04, 2024
  
  855c262a
- [Benchmark] Add `--async-engine` option to benchmark_throughput.py (#7964) · d4db9f53
  Nick Hill authored Sep 03, 2024
  
  d4db9f53
31 Aug, 2024 1 commit
- [Frontend][VLM] Add support for multiple multi-modal items (#8049) · 5231f089
  Roger Wang authored Aug 31, 2024
  
  5231f089
29 Aug, 2024 1 commit
- [Frontend] Minor optimizations to zmq decoupled front-end (#7957) · 4289cad3
  Nick Hill authored Aug 28, 2024
```
Co-authored-by: Robert Shaw <rshaw@neuralmagic>
```
  4289cad3
28 Aug, 2024 1 commit
- [mypy][CI/Build] Fix mypy errors (#7929) · 51f86bf4
  Cyrus Leung authored Aug 28, 2024
  
  51f86bf4
27 Aug, 2024 1 commit
- [Model] Add Mistral Tokenization to improve robustness and chat encoding (#7739) · 6fc4e6e0
  Patrick von Platen authored Aug 27, 2024
  
  6fc4e6e0
26 Aug, 2024 1 commit
- [Bugfix]: Use float32 for base64 embedding (#7855) · 0b769992
  ℍ𝕠𝕝𝕝𝕠𝕨 𝕄𝕒𝕟 authored Aug 26, 2024
```
Signed-off-by: Hollow Man <hollowman@opensuse.org>
```
  0b769992
24 Aug, 2024 2 commits
- [Frontend] add json_schema support from OpenAI protocol (#7654) · d81abefd
  Tyler Rockwood authored Aug 24, 2024
  
  d81abefd
- [Frontend] Publish Prometheus metrics in run_batch API (#7641) · 8da48e4d
  Pooya Davoodi authored Aug 23, 2024
  
  8da48e4d
23 Aug, 2024 1 commit
- [Bugfix] Fix run_batch logger (#7640) · 6885fde3
  Pooya Davoodi authored Aug 23, 2024
  
  6885fde3
22 Aug, 2024 2 commits
- [Frontend] error suppression cleanup (#7786) · b903e1ba
  Joe Runde authored Aug 22, 2024
```
Signed-off-by: Joe Runde <Joseph.Runde@ibm.com>
```
  b903e1ba
- [Bug][Frontend] Improve ZMQ client robustness (#7443) · cde9183b
  Joe Runde authored Aug 21, 2024
```
Signed-off-by: Joe Runde <Joseph.Runde@ibm.com>
```
  cde9183b
21 Aug, 2024 4 commits
- [misc] Add Torch profiler support (#7451) · dd53c4b0
  William Lin authored Aug 21, 2024
```
Co-authored-by: Cody Yu <hao.yu.cody@gmail.com>
```
  dd53c4b0
- [Frontend] Improve Startup Failure UX (#7716) · 970dfdc0
  Robert Shaw authored Aug 21, 2024
  
  970dfdc0
- [Bugfix][Frontend] Fix Issues Under High Load With `zeromq` Frontend (#7394) · f7e3b0c5
  Robert Shaw authored Aug 21, 2024
```
Co-authored-by: Nick Hill <nickhill@us.ibm.com>
```
  f7e3b0c5
- [mypy] Enable following imports for entrypoints (#7248) · baaedfdb
  Cyrus Leung authored Aug 21, 2024
```
Co-authored-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
Co-authored-by: Fei <dfdfcai4@gmail.com>
```
  baaedfdb
18 Aug, 2024 1 commit
- [ Bugfix ] Fix Prometheus Metrics With `zeromq` Frontend (#7279) · e3b31821
  Robert Shaw authored Aug 18, 2024
```
Co-authored-by: Nick Hill <nickhill@us.ibm.com>
```
  e3b31821
17 Aug, 2024 1 commit
- [Bugfix] Clear engine reference in AsyncEngineRPCServer (#7618) · bae888cb
  Rui Qiao authored Aug 16, 2024
```
Signed-off-by: Rui Qiao <ruisearch42@gmail.com>
```
  bae888cb
16 Aug, 2024 4 commits
- [Bugfix][Hardware][AMD][Frontend] add quantization param to embedding checking method (#7513) · 0e39a33c
  Gordon Wong authored Aug 17, 2024
  
  0e39a33c
- [Core] Use uvloop with zmq-decoupled front-end (#7570) · 9587b050
  Nick Hill authored Aug 15, 2024
  
  9587b050
- [Feature]: Add OpenAI server prompt_logprobs support #6508 (#7453) · f878c8fe
  Grant Pinkert authored Aug 16, 2024
  
  f878c8fe
- [Bugfix][Harmless] Fix float16 dtype for model_is_embedding (#7566) · 9c8e2d11
  Michael Goin authored Aug 15, 2024
  
  9c8e2d11
14 Aug, 2024 1 commit
- [Bugfix][Frontend] Disable embedding API for chat models (#7504) · 67d115db
  jack authored Aug 15, 2024
```
Co-authored-by: jack <jack@alex>
```
  67d115db