* docs: Metal expert-matmul backend design (Apple Silicon)
Empirically-validated design for a batched MoE expert-matmul Metal backend.
Microbenchmarks (scratchpad) establish: runtime-compiled Metal needs no Xcode;
V3 (float4 + threadgroup reduction) kernel is correct and fast; synchronous
per-matmul dispatch loses to CPU due to ~150us Metal launch latency, so the win
is batched full-layer dispatch (854us/layer, 707 GFLOP/s) reading expert slabs
zero-copy from unified memory.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* metal: backend infrastructure + kernel-correctness test (M1)
Add backend_metal.{h,mm} — an opt-in Apple-GPU backend built with METAL=1 on
macOS. Runtime-compiled shader (no Xcode needed), zero-copy over unified memory.
Implements coli_metal_matmul (general quantized GEMV, f32/int8/int4/int2) via a
threadgroup-reduction + float4 kernel; batched moe_block is stubbed (returns 0 ->
CPU fallback) for M2. tests/test_backend_metal.mm validates all formats and edge
shapes (odd S, non-mult-4 dims) against a CPU reference (nerr ~2e-6). Makefile
gains a METAL=1 Darwin branch and a metal-test target. Default build unchanged.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* metal: batched moe_block + zero-copy slab registry (M2 backend)
Implement coli_metal_moe_block: gate/up/silu/down for a whole expert block in ONE
command buffer, with GPU memory barriers between stages and BINDLESS gpuAddress
pointers so each expert is read zero-copy from its own RAM slab (exceeds Metal's
~31 buffer-binding limit). coli_metal_register/unregister wrap page-aligned slabs
via newBufferWithBytesNoCopy and resolve interior pointers to GPU addresses.
Per-row ragged expert routing supported; CPU does the final weighted scatter-add.
test_backend_metal validates decode + ragged blocks vs a CPU reference (nerr ~2e-6).
Still gated off in glm.c until the moe() wiring lands.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* metal: wire batched moe_block into glm.c, token-exact (M2 integration)
moe() now dispatches each routed-expert block through the GPU in one command
buffer when COLI_METAL=1, reading expert weights zero-copy from page-aligned
RAM slabs (registered in expert_load). Falls back to CPU per-block on any
unresolved slab or GPU fault. Default build byte-identical (all #ifdef COLI_METAL).
Fixes a heap-corruption crash: expert_load registers slabs from parallel OpenMP
threads, so the slab registry is now mutex-guarded (buffer creation stays outside
the lock). Added command-buffer error checking (fall back to CPU on GPU fault)
and a COLI_METAL_DEBUG one-shot trace.
Validated token-exact vs the CPU path (greedy): identical 12-token output;
expert-matmul time 29.9s -> 21.1s with pinned experts still on CPU.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* metal: instrument moe_block (GPU/CPU split, wall-vs-kernel time)
Add diagnostics printed on the PROFILO line under COLI_METAL: GPU vs CPU-fallback
block counts, experts-on-GPU, and a per-block time split (setup / gpu-wall /
kernel / scatter). Reveals that with a warm cache all experts run on the GPU
(0 fallback) and expert-matmul drops ~1.3x vs CPU, but ~62% of GPU wall-time is
idle/scheduling latency (3.1s kernel of 8.3s wall over 396 sporadic submits) —
the GPU powers down between blocks because attention runs on the CPU per layer.
Points the next optimization at keeping the GPU hot (offload attention).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* docs: Metal backend measured results + next levers
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* docs: Phase 2 fused decode attention plan + absorption-core validated
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* metal: fused decode attention on GPU, token-exact (Phase 2)
coli_metal_attn_decode runs a full S=1 decode attention layer in ONE command
buffer: q_a -> rmsnorm -> q_b -> RoPE ; kv_a -> latent rmsnorm@pos + krot RoPE@pos
(cache write) ; MLA absorption core (qabs/score/softmax/clat/ctx) ; o_proj. The
absorption-core kernels were validated in isolation (nerr ~1e-6) before wiring.
Projection matmuls reuse the mm_gemv kernel; attention weights are uploaded+cached
(serial path, no lock); Lc/Rc caches are page-aligned + registered in kv_alloc for
zero-copy GPU read/write. GLM-5.2 dims compiled in; falls back to CPU for S>1
(prefill/MTP verify), st0!=0, active DSA selection (context>topk), or mismatched
dims. DSA index-key write stays on CPU so future selection still works.
Validated token-exact vs CPU (identical greedy output); attention time 16.5s ->
10.5s (~1.57x), end-to-end 0.20 -> 0.28 tok/s.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* docs: Phase 2 fused attention complete + known limits
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* metal: attention coverage/latency instrumentation + honest results
Add per-layer fused-attention counters (METAL-ATTN line): GPU layer count, gpu-wall
and true kernel time. Measurement (DRAFT=0, all-S=1 decode) shows the fused attention
triggers on all decode layers but is submit-latency-bound: gpu-wall 3.70s vs kernel
0.63s (83% idle latency over 546 sporadic command buffers). Attention time is neutral
vs CPU; the earlier MTP-on "16.5->10.5" was run-to-run variance. Design doc corrected
with the honest result: both offloads are gated by Metal's ~5ms cold-GPU submit
latency; reducing submit count (fuse attention+experts per layer) is the real lever.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* metal: fused attention handles S<=4 (covers MTP verify forwards)
Extend coli_metal_attn_decode from S=1 to S<=4: the core kernels (qabs/score/
smax/clat/ctx) gain a query-row dimension with per-row causal masking (query s
attends keys [0, pos_base+s]); rmsnorm/rope/copy became row-aware; projections
run S rows via mm_gemv. This covers the default MTP config (draft=3 -> S=4 verify
forwards), which previously fell back to CPU attention entirely.
Token-exact vs CPU (identical greedy output, MTP on). Perf is inconclusive at
short context: still submit-latency-bound (attn gpu-wall 5.5s vs kernel 0.9s) and
the measurement is dominated by disk-streaming variance (+/-15s between runs).
Next: measure with a fully-warm cache to isolate compute, then reduce submit count.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* docs: clean warm A/B shows real ~1.4x (experts+S<=4 attention), token-exact
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* metal: interleave attention q/kv paths, 7->4 barriers (iter 2)
The q-path (q_a->rmsnorm->q_b->rope) and kv-path (kv_a->copy->rmsnorm+rope) are
independent until the absorption core, but were serialized by memory barriers.
Interleave them into 4 barrier-separated stages so the GPU overlaps independent
dispatches. Token-exact; attention gpu-wall 3.04s -> 2.73s (~10%).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* metal: zero-copy attention weights + fuse shared expert into GPU block (iter 2)
Dense QT weights/scales now allocate page-aligned + registered (qalloc) under
METAL, so the fused attention reads q_a/q_b/kv_a/kv_b/o zero-copy instead of
uploading ~6 GB of duplicates (RSS -3 GB, upload copies gone). bind_gemv resolves
registered pointers (buffer,offset) with a pre-check guard.
Phase E's shared expert (identical shapes to a routed expert: gate/up [I,D],
down [D,I], same int4 container) is appended to the first Metal moe_block as an
extra expert with rw=1.0 over all S rows — removes 3 CPU matmuls per layer and
fills the same GPU submit. CPU Phase E still runs on any fallback.
Zero-copy validated token-exact: 35.1s -> 29.7s (0.34 tok/s) warm.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* docs: iteration 2 findings
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* docs: iter 2 final ~1.56x + iter 3 plan (disk/GPU overlap)
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* metal: overlap disk loads with GPU compute inside the layer (iter 3)
Split each MoE block into two GPU submits: the RESIDENT experts (pin/LRU hits,
plus the fused shared expert) are encoded and committed BEFORE the missed
experts' OMP pread loop, so the GPU computes while the disk reads; the missed
subset follows in a second (sync) submit once loaded. New two-phase backend API
(coli_metal_moe_block_begin/end) with handle-owned scratch so the async submit
cannot collide with the sync path's static buffers; moe_submit/moe_finish are
shared by both. Per-subset CPU fallback preserved (resident and missed fall back
independently on unresolved slab or GPU fault).
Token-exact. Warm 96GB: expert-matmul 8.96 -> 4.92s (resident compute now hidden
inside the disk window; expert idle latency ~5.7s -> ~0.9s), total 28.97s
(0.35 tok/s) vs CPU 50.2s = ~1.73x.
Note: 'make glm METAL=1' after a default build does NOT rebuild (target looks
up-to-date) — touch glm.c or clean when switching build flavors.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* docs: iter 3 disk/GPU overlap results (~1.73x)
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* metal: keep-alive spinner experiment (env-gated) + latency decomposition
COLI_METAL_SPIN=1 keeps trivial GPU work in flight on a separate queue to probe
whether inter-submit idle is clock ramp-down; thread is detached (a joinable
global thread std::terminate'd the process at exit). First contended A/B was
inconclusive but showed the spinner does NOT collapse attention wall per-call
(~16ms both ways), so ramp-down is not the whole story. METAL-ATTN now decomposes
latency: cpu-sched (commit->kernelStart) vs gpu-sched (kernelStart->GPUStart) vs
kernel execution, to pinpoint where the ~13ms/call goes. Default behavior
unchanged (spinner off).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* metal: standalone regression tests for fused decode attention
run_attn builds full-size fake GLM-5.2 attention weights (int4, page-aligned,
registered), replicates glm.c's absorb-branch math exactly on the CPU (q_a ->
rmsnorm -> q_b -> rope; kv_a -> latent rmsnorm + krot rope -> cache; per-head
qabs/score/softmax/clat/ctx; o_proj), and checks coli_metal_attn_decode against
it at S=1/3/4 and pos_base 0/12/37 — including the Lc/Rc cache write-back, which
end-to-end runs cannot isolate. All pass (nerr ~5e-6, cache ~1.4e-5). The whole
Metal path (gemv, moe_block, fused attention) is now testable without the model.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* metal: route large row-batch matmul_qt GEMMs to the GPU (prefill)
matmul_qt now dispatches to a new coli_metal_gemm when S >= COLI_METAL_GEMM_MIN
(default 16), the weight is int8/int4 and registered (all dense QT allocs are,
via qalloc), and we're not inside an OpenMP region (mirrors the CUDA guard).
Decode-sized matmuls stay on the CPU where NEON wins vs submit latency; prefill's
big GEMMs (kv_b reconstruction at S=Tk, o_proj, dense MLP, step_all's S x vocab
logits) amortize it — microbench showed ~6x over the CPU idot at S=16.
Standalone test: registered int4 GEMM S=64 vs cpu_ref (nerr 2.9e-6).
Machine busy again; end-to-end token-exactness + threshold sweep pending idle.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* README: document the experimental Metal backend (Apple Silicon)
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* metal: 1.5-2.1x faster moe_gemv (simdgroup-per-row + 8-value loads)
Replace one-threadgroup-per-output-row (128 threads reducing via threadgroup
memory) with one SIMDGROUP per output row, 4 rows per threadgroup, and uchar4
loads (8 nibbles / 8 int8 per lane-iteration). Removes the threadgroup barrier
+ shared-memory reduction entirely (simd_sum only) and doubles load width.
Engine-like block-shape microbench (pure GPU time): S=4 block 2548->1739us,
S=1 block 934->437us, big block 4582->3414us — 358-389 GB/s vs 182-264.
Row-bound guard added (NT) since the grid rounds up to 4 rows/TG.
All backend tests pass (moe_block nerr 2.4e-6, attention unchanged).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* metal: mm_gemv simdgroup-per-row + 8-value loads (attention projections, prefill GEMM)
Apply the moe_gemv V2 transformation to the general quantized GEMV: one simdgroup
per output element (4/threadgroup), 8-value loads for i8/i4/f32, no threadgroup
reduction. Same measured 1.5-2.1x class of win; serves the fused-attention
projections (q_a/q_b/kv_a/o), coli_metal_gemm (prefill), and coli_metal_matmul.
All three dispatch sites updated (NT row-bound guard, grid ceil(NT/4) x 128).
Full test suite green, incl. non-mult-of-8 tail paths (2050x6146) and all fmts.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* metal: experimental COLI_MMAP=1 — experts as zero-copy views into mmap'd files
Lazily mmap each safetensors file (PROT_READ, MAP_SHARED, mutex-guarded — expert
loads are OMP-parallel), register the mapping with Metal, and make expert_load a
pointer assignment into the map: no pread, no slab, no copy; the OS page cache is
the cache. Alignment guards fall back to the slab path. Default OFF.
First validation (machine at load 66 + 46GB swap): token-exact, RSS 58 -> 10.5 GB
as designed, but GPU wall exploded (~130 MB/s effective) — the GPU demand-faults
file-backed pages, catastrophic when memory pressure evicts them. Needs an
idle-machine A/B to judge fairly (llama.cpp's identical technique relies on pages
staying resident); possible fixes if slow even idle: CPU pre-touch of missed
experts' pages before the GPU submit, or madvise/mlock windows.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* metal: CPU pre-touch for COLI_MMAP expert pages (fix GPU demand-faulting)
In mmap mode, fault the missed expert's pages in on the CPU inside expert_load
(madvise WILLNEED for async readahead + a page-stride touch): this is pread's I/O
without the copy and without the slab, it runs inside the existing OMP loop that
overlaps with the resident-experts GPU submit (iter 3), and it guarantees the GPU
only ever reads resident pages — GPU demand-faulting of file-backed pages
measured catastrophic (~130 MB/s). Read-only addition: outputs unchanged from the
validated mmap run; perf pending the idle-machine A/B.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* docs: idle-machine suite results (~1.33x same-session; mmap negative result)
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* metal: COLI_METAL_UNTRACKED experiment (negative result, default off)
Env-gated MTLResourceHazardTrackingModeUntracked on registered wraps + scratch to
test whether cross-CB hazard tracking causes the ~10ms/CB gpu-sched delay. Idle
A/B: no effect (gpu-sched 3.9 vs 3.4s, noise), token-exact. Together with the
spinner negative, this pins the attention CB delay as inherent scheduler/wake
overhead on an empty pipeline — removable only by eliminating the CB boundary,
which CPU-side routing at ~58% hit-rate forces. Metal side is at its floor:
kernel 3.5s+0.8s (near BW ceiling), sched ~3.2s, disk ~15s dominant (10 tok).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* docs: loop conclusion — best config DIRECT=1+COLI_METAL=1, 0.42 tok/s (~1.4x)
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* metal: refactor attention into encode_attention()+resolve_attn() (layer-CB prep)
Behavior-preserving: attn_decode is now a thin wrapper; all attention tests
byte-identical. Prepares embedding the chain in a full-layer command buffer.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* metal: full decode layer in ONE command buffer (token-exact)
coli_metal_layer_decode runs the whole layer prelude on the GPU in a single
submit: in_ln rmsnorm -> fused attention -> residual add -> post_ln rmsnorm ->
shared expert (gate/up/silu/down) -> router (f32 simdgroup matvec + sigmoid) ->
exact phase-A top-K selection (greedy argmax over sigmoid+bias with CPU tie
order, --topp truncation, norm_topk, routed_scale) in a serial-per-row kernel.
The CPU's per-layer work shrinks to: read 8 expert IDs, resolve/load, expert CBs
(disk/GPU overlap unchanged), scatter. moe() consumes the precomputed routing
(g_pre_*: skips phase A, keeps eusage/eheat/ereq counters for the learning
cache) and adds the GPU shared-expert output instead of computing phase E.
ld() tensors (norms/router/bias) now allocate registered so the GPU reads them
zero-copy. DSA index keys still computed on CPU from the in_ln-normed x (new
inrm output). Every missing condition falls back to the full CPU layer.
Validated token-exact vs CPU (identical greedy output, MTP on). Profile:
"altro" 3.8s -> 0.53s (12 tok); 0.42 tok/s despite disk-variance headwind.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* docs: Phase 3 full-layer CB results — 0.43 tok/s record, token-exact
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* gitignore: Metal build artifacts, venv, bench datasets
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* remove internal design docs before PR
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Records the July 12-13 lab findings on one 6x RTX 5090 machine:
- vLLM-Moet comparison and why per-rank expert residency dominates
- colibri full-resident placement: 2.30 -> 6.28-6.84 tok/s, with the
tested-and-rejected directions documented
- MTP speculation: broken int4 head identified (issue #8), int8 head
reaches 69-79% acceptance but MoE verify batches scale expert cost
with S, so speculation loses at every depth; revisit after GPU
grouped GEMM
- AVX-512 int4 kernel qualification: numerically better than the old
order, quality-neutral (ppl delta 0.24%), +4-7% on CPU-heavy routing
README links the record from the honest-numbers section.
New byte-level GBNF-subset engine (c/grammar.h: parser + set-of-stacks PDA
walker) wired into spec_decode as a third draft source ("metodo F"), tried
before MTP/n-gram. Wherever the grammar admits exactly one legal byte, the
forced span is tokenized and injected as drafts; the existing batch-union
verification confirms them, so a wrong or out-of-sync grammar can never
change the output. Lazy arming skips preambles; adaptive guard (same
pattern as MTP) disables the source below 50% acceptance; grammar-accepted
tokens no longer pollute the MTP acceptance counter.
GRAMMAR=file.gbnf enables it in run and serve modes (also with DRAFT=0 and
with the int4 MTP head from #8); GRAMMAR_DRAFT=n caps the span (default 24).
Measured on M3 Max / int8-MTP container, greedy, MTP=0 DRAFT=0, NDJSON
classification: 0.37 -> 0.50 tok/s (1.60 tok/forward, 81 fw per 130 tok),
100% acceptance (48/48), output byte-identical to baseline.
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
serve mode persists the compressed MLA KV-cache incrementally after every
turn (~182 KB/token appended, header count written last = crash-safe) and
resumes it at startup: the model remembers the whole conversation and zero
re-prefill happens. :reset and context-full restarts truncate the file.
The MTP layer's KV row is not saved; kv_start=-1 re-arms its decode window.
Validated: split-session answer byte-identical to an uninterrupted session
(tiny oracle, TEMP=0), and on the real 744B model a restarted chat resumed
58 tokens in 0.0s and recalled a fact from the previous session while
prefilling only the new question.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Measured on GLM-5.2 (48 tok, greedy): next-layer routing is 71.6% predictable
one full layer ahead (79.4% skipping attention only; 41.3% previous-token).
PILOT=1 issues next-layer expert WILLNEED from a dedicated I/O thread while
the current layer computes — inline fadvise BLOCKS ~0.5ms/call on a saturated
disk queue (+92s/48 tok, measured), hence the lock-free ring + worker.
Neutral-in-noise on this dev box (disk already ~80% duty); expected to pay on
balanced machines (#12: 43% disk / 46% matmul) — opt-in, default off.
cap_for_ram now RAISES the LRU cap up to the RAM budget (ceiling n_experts,
CAP_RAISE=0 opt-out): big-RAM machines were silently running with cap=8
(#12: 128GB box using 22GB of a 110GB budget; #13: 92GB box, same).
DRAFT=3 on cold cache measured locally: 1399s vs 880s baseline for the same
48 tokens (acceptance 16%, experts/token 1809 vs 800) — confirms #8; DRAFT
re-evaluation belongs to warm-cache serve sessions.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
First real datapoint for the 'Got a better machine?' section: disk iobench
plus stock and --topp 0.7 inference numbers, with the RAM-bound takeaway.
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
Each architecture maps to its own engine binary (glm today; gptoss, qwenmoe
reserved). Registry in c/models.json (local, gitignored); chat shows a picker
when more than one model is installed. Dense models stay llama.cpp territory
- documented honestly in the README.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
JustVugg