[Docs] Use gen-files for generated docs content (#49587)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
This commit is contained in:
@@ -1,15 +1,9 @@
|
||||
# Attention Backend Feature Support
|
||||
|
||||
This document is auto-generated by `tools/pre_commit/generate_attention_backend_docs.py`.
|
||||
It shows the feature support for each registered attention backend
|
||||
based on the checks in `AttentionBackend.validate_configuration()`.
|
||||
|
||||
**Do not edit this file manually.** Run the following command to
|
||||
regenerate it:
|
||||
|
||||
```bash
|
||||
python tools/pre_commit/generate_attention_backend_docs.py
|
||||
```
|
||||
The priority and feature tables on this page are auto-generated from the
|
||||
attention backend registry by
|
||||
`docs/mkdocs/gen_files/generate_attention_backends.py`, based on the checks in
|
||||
`AttentionBackend.validate_configuration()`.
|
||||
|
||||
## Setting the Attention Backend
|
||||
|
||||
@@ -98,40 +92,11 @@ Priority is **1 = highest** (tried first).
|
||||
|
||||
### Standard Attention (MHA, MQA, GQA)
|
||||
|
||||
**Blackwell (SM 10.x):**
|
||||
|
||||
| Priority | Backend |
|
||||
| -------- | ------- |
|
||||
| 1 | `FLASHINFER` |
|
||||
| 2 | `FLASH_ATTN` |
|
||||
| 3 | `TRITON_ATTN` |
|
||||
| 4 | `FLEX_ATTENTION` |
|
||||
| 5 | `TURBOQUANT` |
|
||||
|
||||
**Ampere/Hopper (SM 8.x-9.x):**
|
||||
|
||||
| Priority | Backend |
|
||||
| -------- | ------- |
|
||||
| 1 | `FLASH_ATTN` |
|
||||
| 2 | `FLASHINFER` |
|
||||
| 3 | `TRITON_ATTN` |
|
||||
| 4 | `FLEX_ATTENTION` |
|
||||
| 5 | `TURBOQUANT` |
|
||||
--8<-- "gen:priority-standard"
|
||||
|
||||
### MLA Attention (DeepSeek-style)
|
||||
|
||||
**Blackwell (SM 10.x):**
|
||||
|
||||
| Priority | Backend |
|
||||
| -------- | ------- |
|
||||
| 1 | `FLASHINFER_MLA` |
|
||||
| 2 | `TOKENSPEED_MLA` |
|
||||
| 3 | `CUTLASS_MLA` |
|
||||
| 4 | `FLASH_ATTN_MLA` |
|
||||
| 5 | `FLASHMLA` |
|
||||
| 6 | `TRITON_MLA` |
|
||||
| 7 | `FLASHINFER_MLA_SPARSE`**\*** |
|
||||
| 8 | `FLASHMLA_SPARSE` |
|
||||
--8<-- "gen:priority-mla"
|
||||
|
||||
> **\*** For sparse MLA, FP8 KV cache always prefers `FLASHINFER_MLA_SPARSE`. With BF16 KV cache, `FLASHINFER_MLA_SPARSE` is preferred for low query-head counts (<= 16), while `FLASHMLA_SPARSE` is preferred otherwise.
|
||||
>
|
||||
@@ -157,24 +122,7 @@ Priority is **1 = highest** (tried first).
|
||||
|
||||
## Standard Attention (MHA, MQA, GQA) Backends
|
||||
|
||||
| Backend | Version | Dtypes | KV Dtypes | Block Sizes | Head Sizes | Sink | Non-Causal | MM Prefix | DCP | Attention Types | Compute Cap. |
|
||||
| ------- | ------- | ------ | --------- | ----------- | ---------- | ---- | ---------- | --------- | --- | --------------- | ------------ |
|
||||
| `CPU_ATTN` | | fp16, bf16, fp32 | `auto`, `fp8`, `fp8_e4m3`, `fp8_e5m2` | %16 | 32, 64, 80, 96, 112, 128, 160, 192, 224, 256, 512 | ❌ | ✅ | ❌ | ❌ | All | N/A |
|
||||
| `FLASHINFER` | Native† | fp16, bf16 | `auto`, `float16`, `bfloat16`, `fp8`, `fp8_e4m3`, `fp8_e5m2` | 16, 32, 64, 128, 256, 512, 1024 | 64, 128, 256, 512 | ❌ | ✅ | ❌ | ✅ | Decoder | 8.x-9.x |
|
||||
| `FLASHINFER` | XQA† | fp16, bf16 | `auto`, `float16`, `bfloat16`, `fp8`, `fp8_e4m3`, `fp8_e5m2` | 16, 32, 64, 128, 256, 512, 1024 | 64, 128, 256, 512 | ❌ | ❌ | ❌ | ✅ | Decoder | 9.0 |
|
||||
| `FLASHINFER` | trtllm-gen† | fp16, bf16 | `auto`, `float16`, `bfloat16`, `fp8`, `fp8_e4m3`, `fp8_e5m2`, `nvfp4` | 16, 32, 64, 128, 256, 512, 1024 | 64, 128, 256, 512 | ✅ | ✅ | ❌ | ✅ | Decoder | 10.x |
|
||||
| `FLASH_ATTN` | FA2* | fp16, bf16 | `auto`, `float16`, `bfloat16` | %16 | Any | ❌ | ✅ | ❌ | ✅ | All | ≥8.0 |
|
||||
| `FLASH_ATTN` | FA3* | fp16, bf16 | `auto`, `float16`, `bfloat16`, `fp8`, `fp8_e4m3` | %16 | Any | ✅ | ✅ | ❌ | ✅ | All | 9.x |
|
||||
| `FLASH_ATTN` | FA4* | fp16, bf16 | `auto`, `float16`, `bfloat16`, `fp8`, `fp8_e4m3` | %16 | Any | ✅ | ✅ | ❌ | ✅ | All | ≥10.0 |
|
||||
| `FLASH_ATTN_DIFFKV` | | fp16, bf16 | `auto` | Any | Any | ❌ | ❌ | ❌ | ✅ | Decoder | Any |
|
||||
| `FLEX_ATTENTION` | | fp16, bf16, fp32 | `auto`, `float16`, `bfloat16` | %16 | Any | ❌ | ✅ | ✅ | ❌ | Decoder, Encoder Only | Any |
|
||||
| `HPC_ATTN` | | fp16, bf16 | `auto`, `bfloat16`, `fp8_e4m3` | 64 | 128 | ❌ | ❌ | ❌ | ❌ | Decoder | ≥9.0 |
|
||||
| `ROCM_AITER_FA` | | fp16, bf16 | `auto`, `float16`, `bfloat16`, `fp8`, `fp8_e4m3`, `fp8_e5m2` | 16, 32 | 64, 128, 256 | ✅ | ✅ | ❌ | ❌ | Decoder | N/A |
|
||||
| `ROCM_AITER_UNIFIED_ATTN` | | fp16, bf16 | `auto`, `float16`, `bfloat16`, `fp8`, `fp8_e4m3`, `fp8_e5m2` | %16 | Any | ✅ | ❌ | ✅ | ❌ | All | N/A |
|
||||
| `ROCM_ATTN` | | fp16, bf16, fp32 | `auto`, `float16`, `bfloat16`, `fp8`, `fp8_e4m3`, `fp8_e5m2` | %16 | 32, 64, 80, 96, 128, 160, 192, 224, 256 | ❌ | ✅ | ✅ | ❌ | Decoder, Encoder, Encoder Only | N/A |
|
||||
| `TRITON_ATTN` | | fp16, bf16, fp32 | `auto`, `float16`, `bfloat16`, `fp8`, `fp8_e4m3`, `fp8_e5m2`, `int4_per_token_head`, `int8_per_token_head`, `fp8_per_token_head` | %16 | Any | ✅ | ✅ | ✅ | ❌ | All | Any |
|
||||
| `TRITON_ATTN_DIFFKV` | | fp16, bf16 | `auto`, `bfloat16` | Any | Any | ❌ | ❌ | ❌ | ❌ | Decoder | Any |
|
||||
| `TURBOQUANT` | | fp16, bf16 | `turboquant_k8v4`, `turboquant_4bit_nc`, `turboquant_k3v4_nc`, `turboquant_3bit_nc` | 16, 32, 64, 128 | Any | ❌ | ❌ | ❌ | ❌ | Decoder | Any |
|
||||
--8<-- "gen:table-standard"
|
||||
|
||||
> **†** FlashInfer Native is the regular FlashInfer path. XQA is the SM90 decode path exposed through FlashInfer's TRTLLM decode API. trtllm-gen is used on SM100 and supports sinks. Disable XQA/trtllm-gen via `--attention-config.use_trtllm_attention=0`.
|
||||
>
|
||||
@@ -188,9 +136,7 @@ automatic priority lists above. A lightning indexer scores KV blocks, the
|
||||
top-k blocks (plus fixed init/local blocks) are selected, and attention
|
||||
attends only to those blocks; index keys live in a separate side cache.
|
||||
|
||||
| Backend | Dtypes | KV Dtypes | Block Sizes | Head Sizes | Sink | Non-Causal | MM Prefix | DCP | Attention Types | Compute Cap. |
|
||||
| ------- | ------ | --------- | ----------- | ---------- | ---- | ---------- | --------- | --- | --------------- | ------------ |
|
||||
| `MINIMAX_M3_SPARSE` | bf16, fp16 | `bfloat16`, `fp8`, `fp8_e4m3`, `fp8_e5m2` | 128 | 128 | ❌ | ❌ | ❌ | ❌ | Decoder | Any |
|
||||
--8<-- "gen:table-minimax"
|
||||
|
||||
## MLA (Multi-head Latent Attention) Backends
|
||||
|
||||
@@ -203,12 +149,7 @@ To explicitly select a prefill backend, use
|
||||
Otherwise, the prefill backend is selected automatically at runtime based on
|
||||
hardware and configuration.
|
||||
|
||||
| Backend | Description | Dtypes | Compute Cap. | Notes |
|
||||
| ------- | ----------- | ------ | ------------ | ----- |
|
||||
| `FLASH_ATTN`‡ | FlashAttention varlen (FA2/FA3/FA4) | fp16, bf16 | Any | (qk_nope_head_dim=128, qk_rope_head_dim=64, v_head_dim=128) (FA2/FA3/FA4) or (qk_nope_head_dim=64, qk_rope_head_dim=64, v_head_dim=128) (FA2/FA3/FA4) or (qk_nope_head_dim=192, qk_rope_head_dim=64, v_head_dim=256) (FA2/FA3 only) |
|
||||
| `TRTLLM_RAGGED` | TensorRT-LLM ragged attention | fp16, bf16 | 10.x | (qk_nope_head_dim=128, qk_rope_head_dim=64, v_head_dim=128) or (qk_nope_head_dim=192, qk_rope_head_dim=64, v_head_dim=256) only |
|
||||
| `FLASHINFER` | FlashInfer CUTLASS backend | fp16, bf16 | 10.x | (qk_nope_head_dim=128, qk_rope_head_dim=64, v_head_dim=128) only |
|
||||
| `TOKENSPEED_MLA` | | fp16, bf16 | 10.x | (qk_nope_head_dim=128, qk_rope_head_dim=64, v_head_dim=128) only |
|
||||
--8<-- "gen:table-mla-prefill"
|
||||
|
||||
> **‡** Automatic selection tries FlashAttention first. On Blackwell
|
||||
> (SM100), the fallback order is TRT-LLM Ragged, FlashInfer, then
|
||||
@@ -219,22 +160,7 @@ hardware and configuration.
|
||||
MLA decode backends are selected using the standard
|
||||
`-ac.backend=<BACKEND>` argument (e.g., `FLASHMLA`, `TRITON_MLA`).
|
||||
|
||||
| Backend | Dtypes | KV Dtypes | Block Sizes | Head Sizes | Sink | Non-Causal | Sparse | MM Prefix | DCP | Attention Types | Compute Cap. |
|
||||
| ------- | ------ | --------- | ----------- | ---------- | ---- | ---------- | ------ | --------- | --- | --------------- | ------------ |
|
||||
| `CUTLASS_MLA` | fp16, bf16 | `auto`, `float16`, `bfloat16`, `fp8`, `fp8_e4m3` | 128 | Any | ❌ | ❌ | ❌ | ❌ | ✅ | Decoder | 10.x |
|
||||
| `FLASHINFER_MLA` | fp16, bf16 | `auto`, `float16`, `bfloat16`, `fp8`, `fp8_e4m3` | 32, 64 | Any | ❌ | ❌ | ❌ | ❌ | ✅ | Decoder | 10.x |
|
||||
| `FLASHINFER_MLA_SPARSE` | fp16, bf16 | `auto`, `float16`, `bfloat16`, `fp8`, `fp8_e4m3` | 32, 64 | Any | ❌ | ❌ | ❌ | ❌ | ✅ | Decoder | 10.x |
|
||||
| `FLASHINFER_MLA_SPARSE_SM120` | bf16 | `auto`, `fp8`, `fp8_e4m3`, `fp8_ds_mla` | 64, 256 | Any | ❌ | ❌ | ❌ | ❌ | ❌ | Decoder | 12.x |
|
||||
| `FLASHMLA` | fp16, bf16 | `auto`, `float16`, `bfloat16`, `fp8`, `fp8_e4m3` | 64 | Any | ❌ | ❌ | ❌ | ❌ | ✅ | Decoder | 9.x-10.x |
|
||||
| `FLASHMLA_SPARSE` | bf16 | `auto`, `bfloat16`, `fp8_ds_mla` | 64 | 576 | ❌ | ❌ | ✅ | ❌ | ❌ | Decoder | 9.x-10.x |
|
||||
| `FLASH_ATTN_MLA` | fp16, bf16 | `auto`, `float16`, `bfloat16` | %16 | Any | ❌ | ❌ | ❌ | ❌ | ✅ | Decoder | 9.x |
|
||||
| `FLASH_ATTN_MLA_SPARSE` | fp16, bf16 | `auto`, `float16`, `bfloat16` | 64 | Any | ❌ | ❌ | ✅ | ❌ | ❌ | Decoder | 9.x |
|
||||
| `ROCM_AITER_MLA` | fp16, bf16 | `auto`, `float16`, `bfloat16`, `fp8`, `fp8_e4m3`, `fp8_e5m2` | %1 | Any | ❌ | ❌ | ❌ | ❌ | ❌ | Decoder | N/A |
|
||||
| `ROCM_AITER_MLA_SPARSE` | fp16, bf16 | `auto`, `float16`, `bfloat16`, `fp8`, `fp8_e4m3` | 1, 64 | Any | ❌ | ❌ | ✅ | ❌ | ❌ | Decoder | N/A |
|
||||
| `ROCM_AITER_TRITON_MLA` | fp16, bf16 | `auto` | Any | Any | ❌ | ❌ | ❌ | ❌ | ❌ | Decoder | N/A |
|
||||
| `TOKENSPEED_MLA` | fp16, bf16 | `fp8`, `fp8_e4m3` | 32, 64 | Any | ❌ | ❌ | ❌ | ❌ | ✅ | Decoder | 10.x |
|
||||
| `TRITON_MLA` | fp16, bf16 | `auto`, `float16`, `bfloat16`, `fp8`, `fp8_e4m3` | %16 | Any | ❌ | ❌ | ❌ | ❌ | ✅ | Decoder | Any |
|
||||
| `XPU_MLA_SPARSE` | fp16, bf16 | `auto`, `float16`, `bfloat16` | Any | 576 | ❌ | ❌ | ✅ | ❌ | ❌ | Decoder | Any |
|
||||
--8<-- "gen:table-mla-decode"
|
||||
|
||||
### DeepSeek V4 Decode Backends
|
||||
|
||||
@@ -245,8 +171,4 @@ pipeline (compressor + SWA + indexer, 256-token blocks, head 512);
|
||||
default on NVIDIA is `FLASHINFER_MLA_SPARSE_DSV4` on SM12x and
|
||||
`FLASHMLA_SPARSE_DSV4` on other supported CUDA architectures.
|
||||
|
||||
| Backend | Dtypes | KV Dtypes | Block Sizes | Head Sizes | Sink | Non-Causal | Sparse | MM Prefix | DCP | Attention Types | Compute Cap. |
|
||||
| ------- | ------ | --------- | ----------- | ---------- | ---- | ---------- | ------ | --------- | --- | --------------- | ------------ |
|
||||
| `FLASHINFER_MLA_SPARSE_DSV4` | bf16 | `auto`, `bfloat16`, `fp8`, `fp8_e4m3`, `fp8_ds_mla` | 256 | 512 | ✅ | ❌ | ✅ | ❌ | ❌ | Decoder | 10.x, 12.x |
|
||||
| `FLASHMLA_SPARSE_DSV4` | bf16 | `auto`, `fp8_ds_mla`, `fp8` | 256 | 512 | ✅ | ❌ | ✅ | ❌ | ❌ | Decoder | 9.x-10.x |
|
||||
| `ROCM_FLASHMLA_SPARSE_DSV4` | fp16, bf16 | `auto` | Any | Any | ❌ | ❌ | ❌ | ❌ | ❌ | Decoder | N/A |
|
||||
--8<-- "gen:table-mla-v4-decode"
|
||||
|
||||
Reference in New Issue
Block a user