The pattern causes
cudaErrorInvalidValue when gsa_gpu is a non-contiguous expanded view
(e.g., shape (9,) from quantize_nvfp4_gpu_fused during prefill with M>1).
Root cause: copy_() from an expanded/reshaped view can fail when the
source tensor has non-standard strides. The expand() operation creates
a view with stride-0 dimensions that copy_() may not handle correctly
on all CUDA versions.
Fix: Replace all gsa copy_ patterns with scalar assignment:
self._gsa_buf[0] = gsa_gpu[0] # scalar GPU→GPU, graph-capturable
This is simpler, avoids view issues, and is CUDA-graph-compatible.
Applied to: shared_expert.py, moe.py, linear.py, grouped_linear.py
- _output_buf_padded: (max_tokens * n_groups, o_lora_rank) — matches GEMM output
- Extraction: groups are stacked vertically, not horizontally
- Each group's output is (padded_rows, o_lora_rank) with o_lora_rank columns
1. grouped_linear.py: Pre-allocate _scale_a_buf for swizzle
- Same fix as linear.py — avoids torch.zeros per call
- Uses correctly-sized view for pad_and_swizzle_single
2. quantize.py: Replace torch.zeros_like with scalar 0.0
- torch.zeros_like allocates a full tensor every call
- torch.where(cond, 0.0, x) broadcasts scalar — no allocation
Fixes from running Section A detector on B200:
1. single_shot_inference.py: Use pinned CPU buffers for token/position transfer
- dec_tid_buf[0] = python_int causes CPU→GPU sync
- Fixed: write to pinned CPU buffer, then copy_ (async, graph-capturable)
2. grouped_linear.py: Fix expert_offsets Python loop
- expert_offsets[g] = python_int * padded_rows → CPU→GPU sync per iteration
- Fixed: element-wise multiply with pre-allocated range tensor (GPU-only)
3. grouped_linear.py: Vectorized output extraction for T=1 decode
- Python loop z[:, g, :] = out[...] → CPU sync for each slice
- Fixed: GPU gather with pre-computed indices for T=1
4. grouped_linear.py: Pre-allocate output buffer
- torch.empty() per call → allocation inside graph
- Fixed: use self._output_buf (pre-allocated at max size)
5. grouped_linear.py: Pre-allocate expert_offsets_range_buf
- torch.arange() per call → allocation inside graph
- Fixed: compute once at init, reuse via element-wise multiply
- grouped_linear.py: Replace .item() gsa + Python quantize with
quantize_nvfp4_gpu_fused (zero CPU syncs). Flatten all groups
into (G*T, D), single fused kernel launch, GPU-only gsa copy.
- single_shot_inference.py: Reduce torch.cuda.synchronize() to
every 20 steps instead of every step. Gate per-layer diagnostics
to li<3 or li>=58 (avoid 61 .item() calls per decode step).
1. o_a_proj (Nvfp4GroupedLinear): Added load_nvfp4_weight() method
that loads checkpoint NVFP4 weights directly — no more dequant→BF16→requant.
Each group's weight is transposed from (N, K_packed) checkpoint layout
to (K_packed, N) layout expected by the grouped GEMM.
2. lm_head: Quantize BF16 weight to NVFP4 at load time, use production
Nvfp4Linear GEMM instead of F.linear. Runtime gsa for activation.
Frees the 1.8GB BF16 weight after quantization.
3. Hash router (L0-2): Already optimal — tid2eid is an int32 lookup,
no GEMM to accelerate.
The checkpoint's input_scale was designed for training-time FP8 quantization,
not NVFP4 activation quantization. Using it as gsa causes x/gsa to exceed
the E4M3 block scale maximum (448), leading to systematic magnitude loss
in every projection. This accumulates over 61 layers, compressing the
logit range and producing garbage tokens.
Fix: compute gsa at runtime from actual activation magnitude:
gsa = max(|x|) / (6.0 * 448.0)
This ensures x/gsa ≤ 2688 (the maximum representable in E4M3 block scales).
Applied to: Nvfp4Linear, Nvfp4GroupedLinear, Nvfp4MoE, Nvfp4SharedExpert, Router gate
