zenlm/engine
1
0
Fork 0
mirror of https://github.com/zenlm/engine.git synced 2026-10-30 15:00:05 +00:00
Code Issues Packages Projects Releases Wiki Activity
Files
master
engine/mistralrs-quant/kernels/marlin
T
History
Eric BuehlerandGitHub 863f33de71 Reworked and improved attention chunking (#1591) 
* Add chunking to naive attn

* Add it to cublaslt as well

* Even better!

* Clippy

* Remove prompt chunksize apis

* Prompt chunksize logging

* Format

* Determine based on mask type

* Max seq len in device map

* Max seq len in device map

* Format
2025-08-03 07:52:33 -04:00
..
marlin
Split Marlin and Paged Attention kernels for faster build (#1525)
2025-07-02 11:15:20 -04:00
dummy_marlin_kernel.cu
DSV3/R1 fixes (#1173)
2025-03-08 16:56:27 -05:00
marlin_kernel.cuh
Split Marlin and Paged Attention kernels for faster build (#1525)
2025-07-02 11:15:20 -04:00
marlin_matmul_awq_bf16.cu
Split Marlin and Paged Attention kernels for faster build (#1525)
2025-07-02 11:15:20 -04:00
marlin_matmul_awq_f16.cu
Split Marlin and Paged Attention kernels for faster build (#1525)
2025-07-02 11:15:20 -04:00
marlin_matmul_bf16.cu
Split Marlin and Paged Attention kernels for faster build (#1525)
2025-07-02 11:15:20 -04:00
marlin_matmul_f16.cu
Split Marlin and Paged Attention kernels for faster build (#1525)
2025-07-02 11:15:20 -04:00
marlin_repack.cu
Reworked and improved attention chunking (#1591)
2025-08-03 07:52:33 -04:00