🎯
Focusing
- Menlo Park
Block or Report
Block or report jerryzh168
Report abuse
Contact GitHub support about this user’s behavior. Learn more about reporting abuse.
Report abusePinned
-
pytorch
pytorch PublicForked from pytorch/pytorch
Tensors and Dynamic neural networks in Python with strong GPU acceleration
-
codinfox/espresso
codinfox/espresso PublicA minimal high performance parallel neural network framework running on iOS
703 contributions in the last year
| Day of Week | March Mar | April Apr | May May | June Jun | July Jul | August Aug | September Sep | October Oct | November Nov | December Dec | January Jan | February Feb | |||||||||||||||||||||||||||||||||||||||||
| Sunday Sun | |||||||||||||||||||||||||||||||||||||||||||||||||||||
| Monday Mon | |||||||||||||||||||||||||||||||||||||||||||||||||||||
| Tuesday Tue | |||||||||||||||||||||||||||||||||||||||||||||||||||||
| Wednesday Wed | |||||||||||||||||||||||||||||||||||||||||||||||||||||
| Thursday Thu | |||||||||||||||||||||||||||||||||||||||||||||||||||||
| Friday Fri | |||||||||||||||||||||||||||||||||||||||||||||||||||||
| Saturday Sat | |||||||||||||||||||||||||||||||||||||||||||||||||||||
Less
No contributions.
Low contributions.
Medium-low contributions.
Medium-high contributions.
High contributions.
More
Activity overview
Contribution activity
February 2024
Created 8 commits in 4 repositories
Created a pull request in pytorch/executorch that received 11 comments
Add int8 per token dynamic activaiton quant and int4 weight quant for llama2 in executorch
Summary: att Reviewed By: kimishpatel Differential Revision: D53211239
+663
−70
lines changed
•
11
comments
Opened 4 other pull requests in 3 repositories
pytorch-labs/gpt-fast
1
open
1
merged
-
[quant] Add int8 per token dynamic quant + int4 per group quant for ExecuTorch
This contribution was made on Feb 8
-
fixing over padding and GPTQ padding bug
This contribution was made on Feb 7
pytorch/pytorch
1
closed
-
[quant][pt2e][bc-breaking] Set
fold_quantizeto True inconvert_pt2eThis contribution was made on Feb 8
pytorch/executorch
1
closed
-
Set
fold_quantizeto True inconvert_pt2eThis contribution was made on Feb 8
Reviewed 13 pull requests in 3 repositories
pytorch/pytorch
6 pull requests
-
Modify signature of dequantize ops for decomposed quantized Tensor
This contribution was made on Feb 8
-
[export] Remove torch._export.export
This contribution was made on Feb 8
-
[torch][ao] Fix module name filter for pytorch2 quantization for underscores
This contribution was made on Feb 7
-
[Pytorc][Quant] Duplicate dynamic quant chain
This contribution was made on Feb 7
-
[quant][pt2e] Allow users to override train/eval behavior
This contribution was made on Feb 2
-
[pytorch][ao] Update
PerChannelMinMaxObserverdefault_load_from_state_dictThis contribution was made on Feb 1
pytorch-labs/gpt-fast
4 pull requests
-
Remove unnecessary wrapper code
This contribution was made on Feb 9
-
fixing over padding and GPTQ padding bug
This contribution was made on Feb 7
-
fixing circular import
This contribution was made on Feb 6
-
Updating eval for lm_eval 0.4 and 0.3
This contribution was made on Feb 2
pytorch/executorch
3 pull requests
-
[Pytorc][Quant] Duplicate dynamic quant chain
This contribution was made on Feb 7
-
Qualcomm AI Engine Direct - Fold_Quant Enabled
This contribution was made on Feb 1
-
[Executorch][llama2] embedding quantization
This contribution was made on Feb 1





