This website requires JavaScript.
Explore
Help
Sign In
iHore
/
vLLM
Watch
8
Star
0
Fork
0
Code
Issues
Pull Requests
Actions
1
Packages
Projects
Releases
Wiki
Activity
Files
bfdbfa1632ef638db7d201f366c6f46cc26ca2b6
vLLM
/
csrc
/
quantization
/
fused_kernels
T
History
Thien Tran
0fae39a014
[Perf] per_token_group_quant_8bit: multiply by reciprocal instead of dividing per element (
#61343
)
...
Signed-off-by: Thien Tran <
gau.nernst@yahoo.com.sg
>
2026-10-13 21:37:10 +08:00
..
fused_layernorm_dynamic_per_token_quant.cu
[Misc] Consolidate csrc shared headers and prune dead code (
#60721
)
2026-10-12 09:46:22 -07:00
fused_silu_mul_block_quant.cu
[Misc] Consolidate csrc shared headers and prune dead code (
#60721
)
2026-10-12 09:46:22 -07:00
layernorm_utils.cuh
[Perf] per_token_group_quant_8bit: multiply by reciprocal instead of dividing per element (
#61343
)
2026-10-13 21:37:10 +08:00
quant_conversions.cuh
[Misc] Consolidate csrc shared headers and prune dead code (
#60721
)
2026-10-12 09:46:22 -07:00