f28223c9da
Replaces all Python PyTorch fallback attention with native ixformer kernels: Decode path: - ≤32K: paged_attention_v1 (5D KV layout, x=8) — verified on real BI-V100 - >32K: paged_attention_v2 (5D→4D permute) — verified 65K+ on real BI-V100 - Removes _forward_decode_pytorch Python fallback entirely Prefill path (profiling): - _run_sdpa_fallback now uses ixformer.flash_attn_varlen_func - head_dim=256 verified correct (diff<0.004) and 1.7x faster than PyTorch - Falls back to Q-tiling pure-math if ixformer unavailable Also includes: MoE kernel integration, GDN C++ kernels, diagnostic scripts, xllm upstream layer/kernel references, .dockerignore cleanup. All changes verified on real BI-V100 hardware (single card).
29 lines
928 B
Python
29 lines
928 B
Python
#!/usr/bin/env python3
|
|
"""Probe ixformer.vllm_single_query_cached_kv_attention signature and test."""
|
|
import inspect
|
|
import torch
|
|
import ixformer
|
|
|
|
# Print signature
|
|
fn = ixformer.vllm_single_query_cached_kv_attention
|
|
print(f"Signature: {inspect.signature(fn)}")
|
|
|
|
# Also check v2
|
|
if hasattr(ixformer, 'vllm_single_query_cached_kv_attention_v2'):
|
|
fn2 = ixformer.vllm_single_query_cached_kv_attention_v2
|
|
print(f"V2 Signature: {inspect.signature(fn2)}")
|
|
|
|
# Check contrib.vllm_flash_attn if available
|
|
try:
|
|
from ixformer.contrib import vllm_flash_attn
|
|
print(f"\nvllm_flash_attn dir: {[x for x in dir(vllm_flash_attn) if not x.startswith('_')]}")
|
|
except Exception as e:
|
|
print(f"\nvllm_flash_attn: {e}")
|
|
|
|
# Check ixformer.vllm submodule
|
|
try:
|
|
import ixformer.vllm as ixv
|
|
print(f"\nixformer.vllm dir: {[x for x in dir(ixv) if not x.startswith('_')]}")
|
|
except Exception as e:
|
|
print(f"\nixformer.vllm: {e}")
|