turboderp-org/exllamav3
1
0
Fork 0
mirror of https://github.com/turboderp-org/exllamav3.git synced 2026-04-20 14:29:51 +00:00
Code Issues Packages Projects Releases Wiki Activity
740 Commits 3 Branches 30 Tags
0e8dd898743fcfaec644affec0daf2d0bc1447ab
Commit Graph

8 Commits

Author SHA1 Message Date
turboderp
0f2da5d6a7 GEMM: Lock MCG multiplier to 0xCBAC1FED and MUL1 to 0x83DCD12D. Make MCG the default codebook for new models. 2025-10-12 22:09:01 +02:00
turboderp
4829ea43d9 Rework GEMM kernel tuning 2025-10-05 01:30:20 +02:00
turboderp
1284d43c76 GEMM kernel tweaks and tuning 2025-05-25 13:33:39 +02:00
turboderp
d359bcc0d3 Add MCG 3INST and MCG 1MAD (MUL1) experimental quant modes 2025-05-21 19:15:13 +02:00
turboderp
c4867edd0d GEMM kernel optimizations 2025-05-08 22:44:26 +02:00
turboderp
5d470a2978 Refactor GEMM kernel for cooperative launch and fusions, fuse with input/output Had transforms, retune launch configs, split kernel compile into units 2025-05-05 00:54:26 +02:00
turboderp
cf84811485 Add cache quantization 2025-04-22 21:52:33 +02:00
turboderp
543c4b2771 Initial commit 2025-04-06 14:42:49 +02:00