minke.yu/sglang
1
0
Fork 0
Code Issues Pull Requests Actions 13 Packages Projects Releases Wiki Activity

Clean up environ.py: remove dead env vars, unify deprecation handling, move examples to a unit test (#35060)

Browse Source
This commit is contained in:
Lianmin Zheng
2026-08-17 06:53:34 -07:00
committed by GitHub
parent d97b796c16
commit af743371cc
12 changed files with 294 additions and 269 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/docs/hardware-platforms/ascend-npus/model-deployment/best-practices/minimax_m2_5.mdx
+2 -2
View File
@@ -405,7 +405,6 @@ export PYTORCH_NPU_ALLOC_CONF=expandable_segments:True
export SGLANG_DEEPEP_NUM_MAX_DISPATCH_TOKENS_PER_RANK=204800
export SGLANG_ENABLE_OVERLAP_PLAN_STREAM=1
export SGLANG_EXTERNAL_MODEL_PACKAGE=custom_eagle3
export SGLANG_NPU_FUSED_MOE_MODE=2
export SGLANG_SET_CPU_AFFINITY=1
export STREAMS_PER_DEVICE=32
export TASK_QUEUE_ENABLE=1
@@ -428,6 +427,7 @@ python3 -m sglang.launch_server \
--max-prefill-tokens 8192 \
--cuda-graph-bs 1 2 3 4 5 6 \
--moe-a2a-backend ascend_fuseep \
--fuseep-mode 2 \
--deepep-mode auto \
--quantization modelslim \
--speculative-algorithm EAGLE3 \
@@ -509,7 +509,6 @@ export PYTORCH_NPU_ALLOC_CONF=expandable_segments:True
export SGLANG_DEEPEP_NUM_MAX_DISPATCH_TOKENS_PER_RANK=204800
export SGLANG_ENABLE_OVERLAP_PLAN_STREAM=1
export SGLANG_EXTERNAL_MODEL_PACKAGE=custom_eagle3
export SGLANG_NPU_FUSED_MOE_MODE=2
export SGLANG_SET_CPU_AFFINITY=1
export STREAMS_PER_DEVICE=32
export TASK_QUEUE_ENABLE=1
@@ -531,6 +530,7 @@ python3 -m sglang.launch_server \
--max-prefill-tokens 8192 \
--cuda-graph-bs 1 2 4 8 12 16 20 \
--moe-a2a-backend ascend_fuseep \
--fuseep-mode 2 \
--deepep-mode auto \
--quantization modelslim \
--speculative-algorithm EAGLE3 \
docs/docs/references/environment_variables.mdx
-10
View File
@@ -650,11 +650,6 @@ SGLang supports various environment variables that can be used to configure its
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>Enable MoE padding (sets padding size to 128 if value is <code>1</code>, often set to <code>1</code> in Docker builds)</td>
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}>`false`</td>
</tr>
<tr>
<td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}><code>SGLANG_CUTLASS_MOE</code> (deprecated)</td>
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>Use Cutlass FP8 MoE kernel on Blackwell GPUs (deprecated, use --moe-runner-backend=cutlass)</td>
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}>`false`</td>
</tr>
<tr>
<td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}><code>SGLANG_USE_FUSED_PARALLEL_QKNORM</code></td>
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>Use the fused parallel QK RMSNorm kernel for MiniMax-M2.x on CUDA when attention TP size &gt; 1</td>
@@ -2127,11 +2122,6 @@ SGLang supports various environment variables that can be used to configure its
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>If a warmup forward batch takes longer than this many seconds, the server crashes to avoid hanging. <code>-1</code> disables; increase (e.g. to 1800) to accommodate kernel JIT precompile.</td>
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}><code>-1</code></td>
</tr>
<tr>
<td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}><code>SGLANG_ENABLE_GRPC</code></td>
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>Enable the native gRPC server (internal, not yet user-facing).</td>
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}><code>false</code></td>
</tr>
<tr>
<td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}><code>SGLANG_GRPC_PORT</code></td>
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>Port for the native gRPC server.</td>