🍲
Pinned Loading
-
vllm-project/vllm
vllm-project/vllm PublicA high-throughput and memory-efficient inference and serving engine for LLMs
-
-
neuralmagic/deepsparse
neuralmagic/deepsparse PublicSparsity-aware deep learning inference runtime for CPUs
892 contributions in the last year
Day of Week | April Apr | May May | June Jun | July Jul | August Aug | September Sep | October Oct | November Nov | December Dec | January Jan | February Feb | March Mar | |||||||||||||||||||||||||||||||||||||||||
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
Contributed to
vllm-project/vllm,
tlrmchlsmth/dotfiles,
neuralmagic/nm-vllm
and 17 other
repositories
Loading
Contribution activity
April 2025
Reviewed 14 pull requests in 1 repository
vllm-project/vllm
14 pull requests
-
[Model] Support Llama4 in vLLM
This contribution was made on Apr 5
-
[Kernel] Enable FP16 and BF16 CUTLASS MoE kernels
This contribution was made on Apr 4
-
Add cutlass support for blackwell fp8 blockwise gemm
This contribution was made on Apr 4
-
[Kernel][Bugfix] Re-fuse triton moe weight application
This contribution was made on Apr 4
-
Modularize fused experts and integrate PPLX kernels
This contribution was made on Apr 4
-
[Bugfix] Fix default behavior/fallback for pp in v1
This contribution was made on Apr 4
-
[Bugfix] Fix function names in test_block_fp8.py
This contribution was made on Apr 3
-
[Distributed] [ROCM] Fix custom allreduce enable checks
This contribution was made on Apr 3
-
[misc] instruct pytorch to use nvml-based cuda check
This contribution was made on Apr 2
-
[Kernel] moe wna16 marlin kernel
This contribution was made on Apr 2
-
[Model] Add PLaMo2
This contribution was made on Apr 2
-
[Minor] Fused experts refactor
This contribution was made on Apr 2
-
[Model][MiniMaxText01] Support MiniMaxText01 model inference
This contribution was made on Apr 1
-
[Misc] support multi-node data parallel
This contribution was made on Apr 1
Opened 2 issues in 1 repository
vllm-project/vllm
2
open
-
Integrate PPLX-kernels
This contribution was made on Apr 3
-
[RFC]: Data Parallel Attention and Expert Parallel MoEs
This contribution was made on Apr 3
2
contributions
in private repositories
Apr 1