Force eager fused-experts dispatch for layerwise replay - #29
Open
aquilarubra wants to merge 3 commits into
Open
Conversation
Registers Qwen3_5MoeForConditionalGeneration in MODEL_ATTRS and generalizes get_moe() to walk model.model.language_model.layers, not just model.model.layers, for this architecture's nested multimodal wrapper. Adds a matching observer hook config (num_experts/top_k live on .experts/.gate submodules rather than the MoE block itself here). Generalizes the fused-expert pruning branch, which was hardcoded to Llama4's moe.router attribute and nn.Linear-style router with out_features, to also support Qwen3.5's .gate raw weight Parameter. Extracts select_retained_experts() as a standalone function from prune()'s inline body so the same selection logic can be reused outside an in-memory model (disk-based surgery). Signed-off-by: Fabrizio del Tin <devotedmystic@gmail.com>
REAP's layerwise-observer path was RAM-bounded only in appearance: the observer phase loaded the entire model onto CPU via device_map="cpu" before any block-wise logic ran, so peak RSS still scaled with total checkpoint size rather than one layer's size. This makes it possible to prune a checkpoint far larger than available RAM+VRAM. - New src/reap/disk_stream_util.py: reads/writes checkpoint tensors directly from safetensors shards, opening and closing each shard scoped to a single read (deliberately never caches file handles, since a held mmap handle keeps its touched pages resident in RSS). - layerwise_prune.py: replaces the full-RAM device_map="cpu" load with accelerate.init_empty_weights() (meta tensors) plus real materialization of only the embedding table, for local checkpoint directories (Hub model ids keep the original load path). - layerwise_observer.py: generalizes the fused_experts branch's router lookup (was hardcoded to moe.router) and adds a dense all-experts-all-tokens fallback for architectures whose experts need top-k routing args to call (Qwen3.5, unlike Llama4's simpler dense callable convention). Adds dual-mask support (ReplayBatch.causal_mask) so hybrid linear/full-attention models get the correct mask per layer type instead of replaying whichever mask block 0 received. Extends _move_block()/_offload_current_block() to materialize/free a block's real tensors from disk on demand via the new streaming primitive, instead of only supporting already-CPU-resident blocks. Signed-off-by: Fabrizio del Tin <devotedmystic@gmail.com>
transformers >=5.10 dispatches the fused-experts forward to torch._grouped_mm when available, whose meta registration hard-requires BF16 inputs. This layerwise replay runs in float32 (RoPE cos/sin promote hidden states through the chain), so force the eager per-expert loop instead, which is dtype-agnostic. Observer throughput is dominated by disk streaming, not the expert matmul dispatch, so this has no meaningful performance cost. Signed-off-by: Fabrizio del Tin <devotedmystic@gmail.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Depends on #26 (disk-streaming) — stacked on top of it, so the diff includes those commits until it merges; only the last commit is new here.
Recent
transformersversions dispatch the fused-experts forward totorch._grouped_mmwhen available, whose meta registration hard-requires BF16 inputs — but this layerwise replay runs in float32 (RoPE cos/sin promote hidden states through the chain), which crashes. Forces the eager per-expert loop instead, which is dtype-agnostic; observer throughput here is dominated by disk streaming, not the expert matmul dispatch, so this has no meaningful performance cost.