COMMITS
/ examples/models/llava/runner/llava_runner.cpp April 18, 2025
M
Introduce GenerationConfig
Mengwei Liu committed
April 1, 2025
P
[ExecuTorch][Llama] Change runner to enable chunked prefill (#9805)
pytorchbot committed
March 17, 2025
M
Migrate users of llm tokenizer to use pytorch-labs/tokenizers
Mengwei Liu committed
September 14, 2024
D
Move examples/models/... out of the `torch` namespace (#5318)
Dave Bort committed
September 10, 2024
D
[LLava] Fix stats for C++ runner
Digant Desai committed
September 9, 2024
C
Add Echo parameter to multimodal runner (llava) and jni layer (#5181)
Chirag Modi committed
September 6, 2024
D
[Llama] Dump RSS info for Linux
Digant Desai committed
M
[llava] Expose prefill image and prompt APIs
Mengwei Liu committed
September 4, 2024
M
[runner] Print prompt before call into text prefiller
Mengwei Liu committed
September 3, 2024
A
Pass images by value to allow rvalue args.
Anthony Shoumikhin committed
August 23, 2024
M
Reduce the memory usage of logits from O(context_length) to O(1)
Mengtao Yuan committed
August 22, 2024
D
Migrate extension/llm to new namespace
Dave Bort committed
August 21, 2024
L
Allow multiple eos ids
Lunwen He committed
August 16, 2024
M
[llava][21/N] Add llava runner test binary and build script (#4667)
Mengwei Liu committed
August 15, 2024
M
[llava][20/N] Add llava runner using building blocks in e/llm/runner (#4666)
Mengwei Liu committed