COMMITS
/ .ci/scripts/test_llama.sh March 29, 2025
M
Remove old tokenizer/ directory in ExecuTorch
Mengwei Liu committed
March 10, 2025
M
Add pytorch-labs/tokenizers into ET submodules
Mengwei Liu committed
February 18, 2025
S
Automatically put torch in CMAKE_PREFIX_PATH so users/scripts don't have to (#8474)
Scott Wolchok committed
February 12, 2025
P
Reuse GELU implementation from PyTorch core (#8322)
pytorchbot committed
January 23, 2025
K
[ExecuTorch][BE] Split kv cache and SDPA for better code sharing
Kimish Patel committed
January 13, 2025
S
Qualcomm AI Engine Direct - Support QNN 2.28
shewu-quic committed
December 19, 2024
December 12, 2024
M
Fix CI for build-llm-demo (#7308)
Mergen Nachin committed
M
sh clean.sh script that does cleaning (#7108)
Mergen Nachin committed
December 7, 2024
P
[Executorch] Add quantized kv cache to oss ci (#7212)
pytorchbot committed
November 27, 2024
M
Update XNNPACK to 1ed874e65 (#6538)
Max Ren committed
November 25, 2024
D
Fix test-llama-runner-qnn-linux tests (#7055)
David Lin committed
November 23, 2024
C
Add qnn 16a16w quantization test (#7039)
cccclai committed
November 21, 2024
C
Use getops to pass flags and arguments for test_llama.sh
cccclai committed
October 16, 2024
M
Codemod examples/models/llama2 to examples/models/llama (#6302)
Mergen Nachin committed
October 9, 2024
G
Fix reporting backends and dtyep to benchmark results (#6023)
Guang Yang committed
October 1, 2024
D
Add warmup for Llama (#5756)
Digant Desai committed
September 27, 2024
D
Always use two XNNPACK Partitioners (#5573)
Digant Desai committed
September 18, 2024
S
Add test_llama bf16 portable config to CI (#5472)
Scott Wolchok committed
September 10, 2024
S
Qualcomm AI Engine Direct - Uplevel QNN version for ci test (#5174)
shewu-quic committed
September 5, 2024
A
Switch to the new tensor API internally.
Anthony Shoumikhin committed
August 21, 2024
G
Fix stories model name
Guang Yang committed
August 14, 2024
C
Back out "Back out "[executorch][PR] Add stories ci for qnn""
cccclai committed
August 13, 2024
C
Back out "Add stories ci for qnn"
cccclai committed
C
Add stories ci for qnn
cccclai committed
August 12, 2024
G
Fix periodic run and model name for benchmarking
Guang Yang committed
July 31, 2024
G
Add workflow for on-demand benchmarking (#4441)
Guang Yang committed
July 15, 2024
L
Move tokenizer.py into extension/llm/tokenizer (#4255)
Lunwen He committed
July 8, 2024
C
add coreml stories end to end ci (#4161)
Chen Lai committed
July 5, 2024
C
add mps stories end to end in ci (#4137)
Chen Lai committed
May 22, 2024
M
Fix torchchat model not working on demo apps (#3668)
Mengwei Liu committed
May 3, 2024
A
Add suffixes to cmake flags related to building kernels. (#3499)
Anthony Shoumikhin committed
April 18, 2024
M
Add quantized cmake option back to fix build-apple-framework (#3115)
Mengwei Liu committed
April 17, 2024
M
Add quantized op support to llama runner (#3062)
Mengwei Liu committed
April 10, 2024
M
Consolidate EXECUTORCH_BUILD_CUSTOM option (#2935)
Mengwei Liu committed
April 7, 2024
M
Revert "Use new API to register custom ops for llama model (#2840)" (#2912)
Mengwei Liu committed
April 6, 2024
M
Fix llama runner mac CI jobs (#2903)
Mengwei Liu committed
M
Use new API to register custom ops for llama model (#2840)
Mengwei Liu committed
April 5, 2024
M
OSS CI: Test our endorsed llama path
Mergen Nachin committed
March 27, 2024
L
Add xnnpack to llama runner mac & linux CI job (#2677)
Lucy Qiu committed
March 26, 2024
A
Rename quantized and optimized build options for OSS to follow the rest of options. (#2664)
Anthony Shoumikhin committed
A
Turn off optimized kernels so that they don't build and link unless needed. (#2676)
Anthony Shoumikhin committed
February 27, 2024
M
Add model exporting and inferencing steps into Llama runner cmake CI job (#2092)
Mengwei Liu committed
February 15, 2024
L
Llama stories oss ci (#1973)
Lucy Qiu committed