llama.cpp
Q2k interleaving implementation - x86/x64 SIMD
#14373
Merged

Q2k interleaving implementation - x86/x64 SIMD #14373

Srihari-mcw
github-actions github-actions added ggml
Srihari-mcw Srihari-mcw changed the title Q2k interleaving implementation Q2k interleaving implementation - x86/x64 SIMD 274 days ago
Srihari-mcw Srihari-mcw force pushed from 38de3fbd 274 days ago
Srihari-mcw Srihari-mcw force pushed 274 days ago
Srihari-mcw Srihari-mcw force pushed to c2c53bc3 274 days ago
slaren
Srihari-mcw Srihari-mcw force pushed to 3f6c61d7 259 days ago
Srihari-mcw
slaren
slaren approved these changes on 2025-07-17
ggerganov
ggerganov approved these changes on 2025-07-17
Srihari-mcw
ggerganov
ggerganov commented on 2025-07-30
Srihari-mcw Initial Q2_K Block Interleaving Implementation
4039c223
Manogna-Sree Addressed review comments and clean up of the code
39a75900
Srihari-mcw Post rebase fixes
91d216c7
Manogna-Sree Initial CI/CD fixes
2926cfba
Manogna-Sree Update declarations in arch-fallback.h
7a5e23a7
Manogna-Sree Changes for GEMV Q2_K in arch-fallback.h
7023709d
Manogna-Sree Enable repacking only on AVX-512 machines
d45c9f0b
Manogna-Sree Update comments in repack.cpp
d6ee6da5
Manogna-Sree Address q2k comments
a1053fb9
Srihari-mcw Srihari-mcw force pushed to a1053fb9 239 days ago
Srihari-mcw
ggerganov ggerganov merged baad9488 into master 238 days ago

Login to write a write a comment.

Login via GitHub

Reviewers
Assignees
No one assigned
Labels
Milestone