Optimize Qwen sparse attention, prefill convolution and quantized MoE
bd2a9c90
Optimize grouped sparse attention and CUDA weight-only decode
3aad2c65
Fix Qwen NVFP4 CI test APIs and review formatting
19cd01c2
Revert the last three Qwen optimization commits
84d17393
kunal-vaishnavimarked this pull request as ready for review 34 days ago
Optimize native NVFP4 GEMV and add parity probes
6ee0c274
Merge lower NVFP4 GEMV changes into the QSA stack
c00e7085
kunal-vaishnavi
changed the title [CUDA] Optimize packed QSA verification and native NVFP4 GEMV [CUDA] Optimize packed QSA scoring and multi-token verification34 days ago
Merge main and address QMoE layout and dispatch review feedback
4a0e901c
Fix NVFP4 benchmark trailing newline for Ruff
0fa4cc9d
Fix QMoE C++ and Python formatting reported by CI
81af1c59
Merge latest NVFP4 dependency into CUDA optimization stack
c3a17573
Merge current main into refreshed CUDA dependency stack
5a850ad5
Merge current main into offline NVFP4 dependency
54cad1ff
Align packed QSA stack with refreshed offline NVFP4 parent
Login to write a write a comment.
Login via GitHub