-
Red Hat
- Cambridge, MA
-
18:12
- 12h behind - proexpertprog.github.io
Pinned Loading
-
Toggl-and-Google-calendar-integration
Toggl-and-Google-calendar-integration PublicA script that regularly checks updates a Google Calendar with time entries from Toggl
-
USCRPL/mbed-benchtest
USCRPL/mbed-benchtest PublicTools for testing your Mbed OS applications without ever leaving the bench. Collaboration with MIT Rocket Team.
C++ 8
-
Compile-time mock substitution.md
Compile-time mock substitution.md 1## THIS IS STILL A DRAFT - come back soon for an updated version. It has not been tested, just an idea for now.
23# Abstract
4GoogleTest is one of the most popular testing frameworks in C++. It also includes GoogleMock, a comprehensive mocking framework.
5 -
USCRPL/mbed-cmake
USCRPL/mbed-cmake Public archiveUse the power of CMake to create your MBed applications
-
mbed-boilerplate
mbed-boilerplate PublicAn mbed project default structure using mbed-cmake and mbed-benchtest
CMake 1
-
309 contributions in the last year
Skip to contributions year listDay of Week | August Aug | September Sep | October Oct | November Nov | December Dec | January Jan | February Feb | March Mar | April Apr | May May | June Jun | July Jul | |||||||||||||||||||||||||||||||||||||||||
Sunday Sun | |||||||||||||||||||||||||||||||||||||||||||||||||||||
Monday Mon | |||||||||||||||||||||||||||||||||||||||||||||||||||||
Tuesday Tue | |||||||||||||||||||||||||||||||||||||||||||||||||||||
Wednesday Wed | |||||||||||||||||||||||||||||||||||||||||||||||||||||
Thursday Thu | |||||||||||||||||||||||||||||||||||||||||||||||||||||
Friday Fri | |||||||||||||||||||||||||||||||||||||||||||||||||||||
Saturday Sat |
Activity overview
Contribution activity
July 2025
Created 2 commits in 1 repository
Created a pull request in vllm-project/vllm that received 6 comments
[Bugfix] Upgrade depyf to 0.19 and streamline custom pass logging
Essential Elements of an Effective PR Description Checklist The purpose of the PR, such as "Fix some issue (link existing issues this PR will res…
Reviewed 22 pull requests in 1 repository
vllm-project/vllm
22 pull requests
-
[Core] Allow full cudagraph with separate attention routines and orthogonal to compilation, add support for FA2 and FlashInfer
This contribution was made on Jul 29
-
[Feat] Support Flashinfer TRT-LLM FP8-query/output Attention Kernel
This contribution was made on Jul 28
-
Fix Flashinfer Allreduce+Norm enable disable calculation based on
fi_allreduce_fusion_max_token_num
This contribution was made on Jul 21 -
[Misc] DeepEPHighThroughtput - Enable Inductor pass
This contribution was made on Jul 21
-
[CI] Update CODEOWNERS for vllm/compilation
This contribution was made on Jul 18
-
[XPU] Conditionally import CUDA-specific passes to avoid import errors on xpu platform
This contribution was made on Jul 18
-
[Bugfix] VLLM_V1 supports passing other compilation levels
This contribution was made on Jul 16
-
Enable sequence parallelism for full cuda graph without specifying compile sizes
This contribution was made on Jul 16
-
[WIP][RC] Update PyTorch to 2.8.0
This contribution was made on Jul 16
-
[Feature] Add async tensor parallelism for scaled mm
This contribution was made on Jul 15
-
[cold start] replace VLLM_COMPILE_DEPYF with debug_dump_dir
This contribution was made on Jul 15
-
[BugFix] VLLM_DISABLE_COMPILE_CACHE=1 should disable all reads and writes from the cache
This contribution was made on Jul 14
-
[compile][startup] Disable C++ compilation of symbolic shapes
This contribution was made on Jul 14
-
implement issue #20711
This contribution was made on Jul 14
-
[torch.compile][ROCm][V1] Enable attention output FP8 fusion for V1 attention backends
This contribution was made on Jul 10
-
Integration SM100 FlashInfer fused allreduce RMSNorm
This contribution was made on Jul 10
-
[Perf][fp8] Use CustomOp abstraction for fp8 quant for better perf
This contribution was made on Jul 10
-
[CI] Fix pre commit issue
This contribution was made on Jul 10
-
[Doc] Guide for Incremental Compilation Workflow
This contribution was made on Jul 10
-
[Attention] Refactor attention metadata builder interface
This contribution was made on Jul 9
-
[ROCm][FEAT] Enable Full Graph Mode in AITER MLA V1 Attn Backend (Decode Phase only)
This contribution was made on Jul 2
-
[Refactor] Refactor import utils
This contribution was made on Jul 1
Created an issue in vllm-project/vllm that received 5 comments
[Feature]: Use QuantFp8
CustomOp
-abstraction for MoE layers
🚀 The feature, motivation and pitch
#19830 added QuantFp8
, which uses the CustomOp
abstraction to implement fp8 quantization in both CUDA and torch…
Opened 1 other issue in 1 repository
vllm-project/vllm
1
closed
-
[Bug]: depyf integration not working:
AttributeError: 'NoneType' object has no attribute 'dict_getitem'
This contribution was made on Jul 9