core/go-mlx
8
0
Fork 0
Code Issues 1 Pull requests Projects Releases Packages Wiki Activity Actions
32 commits 1 branch 4 tags 1.2 MiB
Commit graph

7 commits

Author SHA1 Message Date
Snider
443347a2f8 fix(metal): address 4 minor code review items 
- Rename New() → newArray() to signal internal-only intent (112 usages)
- Remove unused Collect() function and its test
- Fix discarded json.Unmarshal error in qwen3.go
- Document AsStrided stride formula in gemma3.go

Co-Authored-By: Virgil <virgil@lethean.io>
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
 2026-02-19 21:36:40 +00:00
Snider
f2ca7fe188 docs(cpp): add on-demand research tasks for CLion Claude 
Version bump validation, batch evaluation patterns, GPU profiling,
quantised matmul variants, and async/streaming patterns — all
activate when the Go side needs them.

Co-Authored-By: Virgil <virgil@lethean.io>
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
 2026-02-19 21:01:45 +00:00
Snider
f507620e85 docs(cpp): complete mlx-c API research — all tasks done 
CLion Claude session 1 completed all orientation and priority tasks:
- Full API surface map (180 ops, Go binds ~40)
- mlx_contiguous found (fixes Floats() bug)
- mlx_cumsum found (unblocks TopP sampling)
- Memory management fully documented (refcounted, safe to free)
- Error model documented (free-form strings only)
- Device info API documented (mlx_metal_device_info)

Co-Authored-By: Virgil <virgil@lethean.io>
 2026-02-19 20:40:00 +00:00
Snider
c881813872 docs(design): backend abstraction with internal/metal reorganisation 
Approved design for restructuring go-mlx:
- Root package becomes clean interface (TextModel, LoadModel, Token)
- All CGO code moves to internal/metal/
- Deterministic memory management (Close + per-step cleanup)
- Error propagation instead of silent logging
- mlxlm/ backend placeholder for Python subprocess support

Includes API breaking change communication in FINDINGS.md and
memory management research tasks in cpp/TODO.md.

See: docs/plans/2026-02-19-backend-abstraction-design.md

Co-Authored-By: Virgil <virgil@lethean.io>
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
 2026-02-19 19:12:04 +00:00
Snider
3b155f6ca7 chore(cpp): set up standalone CLion project for parallel C++ sessions 
cpp/ now has its own CMakeLists.txt that independently fetches mlx-c
v0.4.1, allowing a CLion Claude to build and explore the C API surface
without conflicting with the Go-side CMake build. Updated CLAUDE.md to
reflect cpp/ as the project root with standalone build instructions.

Added priority tasks to cpp/TODO.md: mlx_contiguous search, eval
semantics verification, mlx_cumsum check for TopP sampling.

Co-Authored-By: Virgil <virgil@lethean.io>
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
 2026-02-19 18:49:16 +00:00
Snider
28b5c5bb47 test(sub-packages): add 33 tests for cache, sample, tokenizer 
- cache_test.go (10): KVCache and RotatingKVCache — creation, single/multi
  update, bounded sliding window, reset, state access
- sample_test.go (8): greedy, temperature (high/low), topK (single/multi),
  chain composition, TopP/MinP stub pass-through
- tokenizer_test.go (15): Load (valid/missing/invalid), BOS/EOS detection,
  encode produces tokens, decode skips specials, decode regular tokens,
  DecodeToken (regular/special/space/unknown), FormatGemmaPrompt,
  GPT-2 byte maps (round-trip, printable ASCII, control chars)

Total test count: 29 → 148 across 10 test files.

Co-Authored-By: Virgil <virgil@lethean.io>
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
 2026-02-19 18:40:49 +00:00
Snider
37abc496ba test(core): add 86 tests for ops, array, nn, fast kernels 
Phase 1 hardening: cover all previously-untested core operations.

- array_test.go (25): scalar/array creation, shape, clone, free, data access
- ops_test.go (44): arithmetic, math, matmul, reductions, shape ops, indexing, slicing, random
- nn_test.go (8): Linear (dense/bias/LoRA), Embedding, RMSNormModule, RepeatKV
- fast_test.go (9): RMSNorm, LayerNorm, RoPE, ScaledDotProductAttention

Found: Floats()/DataInt32() return wrong data on non-contiguous arrays
(transpose, broadcast, slice views). Documented in FINDINGS.md.

Also: cpp/ workspace docs for CLion Claude session, Go 1.26 impact
assessment, verified go generate → test round-trip (29→115 tests).

Co-Authored-By: Virgil <virgil@lethean.io>
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
 2026-02-19 18:37:30 +00:00