-
Notifications
You must be signed in to change notification settings - Fork 203
Pull requests: openvinotoolkit/openvino.genai
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
LLM: release plugin once pipeline is removed
category: continuous batching
Continuous batching
category: GenAI C++ API
Changes in GenAI C++ public headers
category: LLM
LLM pipeline (stateful, static)
no-match-files
Don't silence a error if a file can't be opened
category: tokenizers
Tokenizer class or submodule update
Add Phi-3.5-vision-instruct and Phi-3-vision-128k-instruct
category: visual language
Visual language pipeline
no-match-files
Increase priority for rt info to fix Phi-3.5-vision-instruct and Phi-3-vision-128k-instruct
category: tokenizers
Tokenizer class or submodule update
no-match-files
[ Speculative decoding ] Support different tokenizers for draft and main models
category: GHA
CI based on Github actions
category: samples
GenAI samples
category: sampling
Sampling / Decoding algorithms
category: speculative decoding
Speculative decoding
#1617
opened Jan 22, 2025 by
iefode
Loading…
[VLM] Set stop token ids from default generation config in VLM pipeline
category: visual language
Visual language pipeline
[WA] Add API to release memory by unload plugin
category: GenAI C++ API
Changes in GenAI C++ public headers
category: LLM
LLM pipeline (stateful, static)
do_not_merge
no-match-files
#1600
opened Jan 20, 2025 by
sammysun0711
•
Draft
Update to the latest tokenizers with StringPack/Unpack from opset
category: tokenizers
Tokenizer class or submodule update
Pass pad_token_id as model compilation parameters
category: LLM
LLM pipeline (stateful, static)
#1556
opened Jan 15, 2025 by
AsyaPronina
Loading…
Cb by default int8 respect ir
category: continuous batching
Continuous batching
category: LLM
LLM pipeline (stateful, static)
category: speculative decoding
Speculative decoding
do_not_merge
no-match-files
Debug qwen
category: LLM
LLM pipeline (stateful, static)
category: NPU
category: samples
GenAI samples
do_not_review
#1537
opened Jan 13, 2025 by
AsyaPronina
•
Draft
Automatically apply chat template in non-chat scenarios
category: cmake / build
Cmake scripts
category: GenAI C++ API
Changes in GenAI C++ public headers
category: GHA
CI based on Github actions
category: llm_bench
Label for tool/llm_bench folder
category: LLM
LLM pipeline (stateful, static)
category: Python API
Python API for GenAI
category: samples
GenAI samples
category: sampling
Sampling / Decoding algorithms
category: tokenizers
Tokenizer class or submodule update
category: visual language
Visual language pipeline
category: WWB
PR changes WWB
no-match-files
[Tokenizers] add max_lengh parametrisation to encode
category: GenAI C++ API
Changes in GenAI C++ public headers
category: Python API
Python API for GenAI
category: tokenizers
Tokenizer class or submodule update
enhancement
New feature or request
Add MSVC Support For UTF-8 in Chat Sample
category: samples
GenAI samples
#1483
opened Jan 6, 2025 by
sammysun0711
Loading…
Add a choice of how to end streaming from callback: STOP or CANCEL
category: continuous batching
Continuous batching
category: GenAI C++ API
Changes in GenAI C++ public headers
category: LLM
LLM pipeline (stateful, static)
category: prompt lookup
category: Python API
Python API for GenAI
category: samples
GenAI samples
category: speculative decoding
Speculative decoding
category: visual language
Visual language pipeline
category: whisper
Whisper pipeline
no-match-files
Concurrency in stable-diffusion image generation
category: cmake / build
Cmake scripts
category: GenAI C++ API
Changes in GenAI C++ public headers
category: samples
GenAI samples
category: text to image
Text 2 image pipeline
no-match-files
Add code quality checks to GitHub Actions
category: cmake / build
Cmake scripts
category: continuous batching
Continuous batching
category: GenAI C++ API
Changes in GenAI C++ public headers
category: GHA
CI based on Github actions
category: llm_bench
Label for tool/llm_bench folder
category: LLM
LLM pipeline (stateful, static)
category: LoRA
Low rank adapters
category: prompt lookup
category: Python API
Python API for GenAI
category: samples
GenAI samples
category: sampling
Sampling / Decoding algorithms
category: speculative decoding
Speculative decoding
category: text to image
Text 2 image pipeline
category: tokenizers
Tokenizer class or submodule update
category: visual language
Visual language pipeline
category: whisper
Whisper pipeline
no-match-files
Pl bench
category: cmake / build
Cmake scripts
category: continuous batching
Continuous batching
category: GenAI C++ API
Changes in GenAI C++ public headers
category: GHA
CI based on Github actions
category: LLM
LLM pipeline (stateful, static)
category: Python API
Python API for GenAI
category: samples
GenAI samples
category: sampling
Sampling / Decoding algorithms
category: speculative decoding
Speculative decoding
no-match-files
Use get_max_new_tokens() insted of max_new_tokens field when stopping…
category: continuous batching
Continuous batching
category: prompt lookup
category: sampling
Sampling / Decoding algorithms
category: speculative decoding
Speculative decoding
#1417
opened Dec 20, 2024 by
michalkulakowski
Loading…
add performance statistics for image generation
category: cmake / build
Cmake scripts
category: GenAI C++ API
Changes in GenAI C++ public headers
category: Python API
Python API for GenAI
category: samples
GenAI samples
category: text to image
Text 2 image pipeline
#1405
opened Dec 18, 2024 by
xufang-lisa
Loading…
Add performance statistics for speculative decoding test
category: continuous batching
Continuous batching
category: prompt lookup
category: samples
GenAI samples
category: speculative decoding
Speculative decoding
#1403
opened Dec 18, 2024 by
xufang-lisa
•
Draft
Previous Next
ProTip!
Filter pull requests by the default branch with base:master.