llama.cpp
ggml webgpu: faster normal quant and some k-quant matrix operations, better shader parameter handling
#20173
Merged
Merged
ggml webgpu: faster normal quant and some k-quant matrix operations, better shader parameter handling #20173
reeselevine
merged
6 commits into
ggml-org:master
from
reeselevine:master
K quant speedup (#20)
52058f3b
Move towards writeBuffer for params
3a0d3e1b
Move away from multiple buffers for set_rows errors, remove host buff…
efab3dfb
Merge remote-tracking branch 'upstream/master'
d77731c2
Remove extra file
02cac094
CISC
approved these changes
on 2026-03-06
Formatting
1dbdc5b8
nikhilJain17
approved these changes
on 2026-03-09
Login to write a write a comment.
Login via GitHub