minke.yu/sglang
1
0
Fork 0
Code Issues Pull Requests Actions 12 Packages Projects Releases Wiki Activity

[Kernel] Migrate scattered quantization kernels to sglang.kernels (RFC #29630, Phase 2.5, 1/7) (#30784)

Browse Source 
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
This commit is contained in:
Xiaoyu Zhang
2026-07-13 16:17:01 +08:00
committed by GitHub
co-authored by Claude Fable 5
parent 2225817424
commit 874fc07d9b
252 changed files with 294 additions and 214 deletions
Download Patch File Download Diff File Expand all files Collapse all files
benchmark/kernels/quantization/bench_int8_quant.py
+1 -1
View File
@@ -5,7 +5,7 @@ import triton
from vllm._custom_ops import scaled_int8_quant as vllm_scaled_int8_quant
from sglang.benchmark.bench_utils import run_bench
from sglang.srt.layers.quantization.int8_kernel import per_token_quant_int8
from sglang.kernels.ops.quantization.int8_kernel import per_token_quant_int8
@torch.compile(backend="inductor")