Delete cutlass_mla, non-Marlin GPTQ, AWQ AOT kernel, and Dual Chunk Flash Attention (#32114)

Co-authored-by: Brayden Zhong <brayden@radixark.ai>

docs/cookbook/autoregressive/DeepSeek/DeepSeek-V3.mdx

@@ -404,7 +404,7 @@ The spec-v2 overlap scheduler is enabled by default. It improves performance by
 DeepSeek V3 uses [Multi-head Latent Attention (MLA)](https://arxiv.org/pdf/2405.04434), an attention mechanism that improves inference efficiency. SGLang implements several optimizations:
 
 - **Weight Absorption:** Reorders matrix multiplications to improve decoding phase efficiency.
-- **MLA Attention Backends:** FA3, Flashinfer, FlashMLA, CutlassMLA, TRTLLM MLA (Blackwell), and Triton. FA3 is the default.
+- **MLA Attention Backends:** FA3, Flashinfer, FlashMLA, TRTLLM MLA (Blackwell), and Triton. FA3 is the default.
 - **FP8 Quantization:** W8A8 FP8 and KV Cache FP8, with BMM operators for weight-absorbed MLA in FP8.
 - **CUDA Graph & Torch.compile:** Both MLA and MoE support CUDA Graph and Torch.compile for reduced decoding latency.
 - **Chunked Prefix Cache:** Increases throughput for long-sequence chunked prefill (FlashAttention3 backend only).

docs/docs/advanced_features/attention_backend.mdx

@@ -664,15 +664,6 @@ python3 -m sglang.launch_server \
   --trust-remote-code
 ```
 
-- Cutlass MLA
-```bash Command
-python3 -m sglang.launch_server \
-  --tp 8 \
-  --model deepseek-ai/DeepSeek-R1 \
-  --attention-backend cutlass_mla \
-  --trust-remote-code
-```
-
 - Ascend
 ```bash Command
 python3 -m sglang.launch_server \
@@ -701,13 +692,6 @@ python3 -m sglang.launch_server \
   --attention-backend flex_attention
 ```
 
-- Dual Chunk FlashAttention
-```bash Command
-python3 -m sglang.launch_server \
-  --model Qwen/Qwen2.5-14B-Instruct-1M \
-  --attention-backend dual_chunk_flash_attn
-```
-
 - Torch Native
 ```bash Command
 python3 -m sglang.launch_server \

docs/docs/advanced_features/quantization.mdx

@@ -89,14 +89,14 @@ The following table summarizes quantization method support across NVIDIA and AMD
       <td>Yes</td>
       <td>Yes</td>
       <td>Yes</td>
-      <td>Uses Triton dequantize on AMD (vs. optimized CUDA kernels on NVIDIA). Uses CANN kernels on Ascend</td>
+      <td>Uses a JIT-compiled CUDA kernel on NVIDIA, Triton dequantize on AMD. Uses CANN kernels on Ascend</td>
     </tr>
     <tr>
       <td><code>gptq</code></td>
+      <td>No</td>
+      <td>No</td>
       <td>Yes</td>
-      <td>Yes</td>
-      <td>Yes</td>
-      <td>Uses Triton or vLLM kernels on AMD. Uses CANN kernels on Ascend</td>
+      <td>Removed on NVIDIA and AMD GPUs — use <code>gptq_marlin</code> instead. Uses CANN kernels on Ascend. Still supported on Intel CPUs with AMX</td>
     </tr>
     <tr>
       <td><code>compressed-tensors</code></td>

docs/docs/advanced_features/server_arguments.mdx

@@ -1418,19 +1418,19 @@ Please consult the documentation below and [server_args.py](https://github.com/s
       <td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}>`--attention-backend`</td>
       <td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>Choose the kernels for attention layers.</td>
       <td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}>`None`</td>
-      <td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}><code>triton</code>, <code>torch_native</code>, <code>flex_attention</code>, <code>dsa</code>, <code>nsa</code>, <code>dsv4</code>, <code>compressed</code>, <code>cutlass_mla</code>, <code>fa3</code>, <code>fa4</code>, <code>flashinfer</code>, <code>flashmla</code>, <code>trtllm_mla</code>, <code>cutedsl_mla</code>, <code>tokenspeed_mla</code>, <code>trtllm_mha</code>, <code>dual_chunk_flash_attn</code>, <code>aiter</code>, <code>wave</code>, <code>intel_amx</code>, <code>ascend</code>, <code>intel_xpu</code></td>
+      <td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}><code>triton</code>, <code>torch_native</code>, <code>flex_attention</code>, <code>dsa</code>, <code>nsa</code>, <code>dsv4</code>, <code>compressed</code>, <code>fa3</code>, <code>fa4</code>, <code>flashinfer</code>, <code>flashmla</code>, <code>trtllm_mla</code>, <code>cutedsl_mla</code>, <code>tokenspeed_mla</code>, <code>trtllm_mha</code>, <code>aiter</code>, <code>wave</code>, <code>intel_amx</code>, <code>ascend</code>, <code>intel_xpu</code></td>
     </tr>
         <tr>
       <td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}>`--prefill-attention-backend`</td>
       <td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>Choose the kernels for prefill attention layers (have priority over --attention-backend).</td>
       <td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}>`None`</td>
-      <td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}><code>triton</code>, <code>torch_native</code>, <code>flex_attention</code>, <code>dsa</code>, <code>nsa</code>, <code>dsv4</code>, <code>compressed</code>, <code>cutlass_mla</code>, <code>fa3</code>, <code>fa4</code>, <code>flashinfer</code>, <code>flashmla</code>, <code>trtllm_mla</code>, <code>cutedsl_mla</code>, <code>tokenspeed_mla</code>, <code>trtllm_mha</code>, <code>dual_chunk_flash_attn</code>, <code>aiter</code>, <code>wave</code>, <code>intel_amx</code>, <code>ascend</code>, <code>intel_xpu</code></td>
+      <td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}><code>triton</code>, <code>torch_native</code>, <code>flex_attention</code>, <code>dsa</code>, <code>nsa</code>, <code>dsv4</code>, <code>compressed</code>, <code>fa3</code>, <code>fa4</code>, <code>flashinfer</code>, <code>flashmla</code>, <code>trtllm_mla</code>, <code>cutedsl_mla</code>, <code>tokenspeed_mla</code>, <code>trtllm_mha</code>, <code>aiter</code>, <code>wave</code>, <code>intel_amx</code>, <code>ascend</code>, <code>intel_xpu</code></td>
     </tr>
         <tr>
       <td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}>`--decode-attention-backend`</td>
       <td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>Choose the kernels for decode attention layers (have priority over --attention-backend).</td>
       <td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}>`None`</td>
-      <td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}><code>triton</code>, <code>torch_native</code>, <code>flex_attention</code>, <code>dsa</code>, <code>nsa</code>, <code>dsv4</code>, <code>compressed</code>, <code>cutlass_mla</code>, <code>fa3</code>, <code>fa4</code>, <code>flashinfer</code>, <code>flashmla</code>, <code>trtllm_mla</code>, <code>cutedsl_mla</code>, <code>tokenspeed_mla</code>, <code>trtllm_mha</code>, <code>dual_chunk_flash_attn</code>, <code>aiter</code>, <code>wave</code>, <code>intel_amx</code>, <code>ascend</code>, <code>intel_xpu</code></td>
+      <td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}><code>triton</code>, <code>torch_native</code>, <code>flex_attention</code>, <code>dsa</code>, <code>nsa</code>, <code>dsv4</code>, <code>compressed</code>, <code>fa3</code>, <code>fa4</code>, <code>flashinfer</code>, <code>flashmla</code>, <code>trtllm_mla</code>, <code>cutedsl_mla</code>, <code>tokenspeed_mla</code>, <code>trtllm_mha</code>, <code>aiter</code>, <code>wave</code>, <code>intel_amx</code>, <code>ascend</code>, <code>intel_xpu</code></td>
     </tr>
         <tr>
       <td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}>`--sampling-backend`</td>