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

[Kernel] Set sgl_per_token_group_quant_8bit_v2 as default choice (#22467)

Browse Source
This commit is contained in:
Baizhou Zhang
2026-04-11 01:59:57 -07:00
committed by GitHub
parent 4f45472f34
commit d14d368191
5 changed files with 29 additions and 19 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/references/environment_variables.md
-1
View File
@@ -122,7 +122,6 @@ SGLang supports various environment variables that can be used to configure its
| Environment Variable | Description | Default Value |
| --- | --- | --- |
| `SGLANG_INT4_WEIGHT` | Enable INT4 weight quantization | `false` |
| `SGLANG_PER_TOKEN_GROUP_QUANT_8BIT_V2` | Apply per token group quantization kernel with fused silu and mul and masked m | `false` |
| `SGLANG_FORCE_FP8_MARLIN` | Force using FP8 MARLIN kernels even if other FP8 kernels are available | `false` |
| `SGLANG_NVFP4_CKPT_FP8_GEMM_IN_ATTN` | Quantize q_b_proj from BF16 to FP8 when launching DeepSeek NVFP4 checkpoint | `false` |
| `SGLANG_MOE_NVFP4_DISPATCH` | Use nvfp4 for moe dispatch (on flashinfer_cutlass or flashinfer_cutedsl moe runner backend) | `"false"` |