This website requires JavaScript.
Explore
Help
Register
Sign In
20231088
/
vllm
Watch
1
Star
0
Fork
0
You've already forked vllm
Code
Issues
Pull Requests
Actions
1
Packages
Projects
Releases
Wiki
Activity
vllm
/
csrc
/
quantization
/
fp8
History
ℍ𝕠𝕝𝕝𝕠𝕨 𝕄𝕒𝕟
a31614e386
[ROCm][Quantization][Kernel] Use FP8 FNUZ when OCP flag is 0 or undefined (
#13851
)
...
Signed-off-by: Hollow Man <hollowman@opensuse.org>
2025-02-27 10:39:10 +08:00
..
amd
[ROCm][Quantization][Kernel] Use FP8 FNUZ when OCP flag is 0 or undefined (
#13851
)
2025-02-27 10:39:10 +08:00
nvidia
[CI/Build] Suppress divide-by-zero and missing return statement warnings (
#7001
)
2024-08-05 16:00:01 -04:00
common.cu
[torch.compile] Fuse RMSNorm with quant (
#9138
)
2024-11-08 21:20:08 +00:00
common.cuh
[ROCm][Quantization][Kernel] Using HIP FP8 header (
#12593
)
2025-02-25 00:39:59 -08:00
fp8_marlin.cu
[CI/Build] Per file CUDA Archs (improve wheel size and dev build times) (
#8845
)
2024-10-03 22:55:25 -04:00