Patrick DevineandGitHub d63b702609 Add ripple preview support to the MLX runner (#19592) ...

Add the Ripple model, renderer, parser and import registration.
Support per-layer NoPE in DFlash drafts.
Fuse MLP activation, value blending and attention gating.
Add reference fixtures and model/runner regression tests.

2026-11-07 16:36:53 -08:00

..

batch

…

cache

MLX, MLX-C: version bump - prompt speed up for gemma/flint/laguna (#19291)

2026-10-25 21:25:58 -07:00

model

Add ripple preview support to the MLX runner (#19592)

2026-11-07 16:36:53 -08:00

nn

mlx: support YaRN scaling in Qwen3 and Qwen3.5 (#19231)

2026-11-04 14:14:32 -08:00

sample

mlx: sort long top-k rows in chunks (#19392)

2026-10-29 18:53:49 -07:00

testdata

Add ripple preview support to the MLX runner (#19592)

2026-11-07 16:36:53 -08:00

tokenizer

…

xgrammar

…

cache_trie_test.go

…

cache_trie.go

…

client_score_test.go

…

client_score.go

…

client_speech_test.go

mlxrunner: add Phonon text-to-speech support (#19166)

2026-10-22 11:36:42 -07:00

client_speech.go

mlxrunner: add Phonon text-to-speech support (#19166)

2026-10-22 11:36:42 -07:00

client_test.go

…

client.go

mlxrunner: add Phonon text-to-speech support (#19166)

2026-10-22 11:36:42 -07:00

dflash_test.go

dflash: add the DFlash2 draft model (#19149)

2026-10-26 16:04:43 -07:00

dflash.go

dflash: add the DFlash2 draft model (#19149)

2026-10-26 16:04:43 -07:00

embed_test.go

…

embed.go

…

grammar_mask_test.go

…

grammar_test.go

…

grammar.go

…

media_test.go

…

media.go

…

mtp_test.go

…

mtp.go

…

pipeline_panic_test.go

…

pipeline_test.go

…

pipeline.go

…

prefix_cache_scenario_test.go

…

prefix_cache_test.go

…

prefix_cache.go

…

ripple_test.go

Add ripple preview support to the MLX runner (#19592)

2026-11-07 16:36:53 -08:00

runner_test.go

MLX: make Qwen3.8 Flash Next memory efficient (#18078)

2026-11-06 13:39:21 -08:00

runner.go

MLX: make Qwen3.8 Flash Next memory efficient (#18078)

2026-11-06 13:39:21 -08:00

score_hidden_test.go

…

score_test.go

…

score.go

…

server.go

mlx: reject unsupported CUDA devices (#19521)

2026-11-04 09:57:25 -08:00

speculate_depth_test.go

…

speculate_depth.go

…

speculate_stats.go

dflash: add the DFlash2 draft model (#19149)

2026-10-26 16:04:43 -07:00

speculate.go

dflash: add the DFlash2 draft model (#19149)

2026-10-26 16:04:43 -07:00

speech.go

llm: LFM3 GGUF fixes and llama-server speech (#19344)

2026-10-27 18:56:22 -07:00

status_memory_test.go

…

status_memory.go

…

utf8_buffer_test.go

…

utf8_buffer.go

…

verify_test.go

Add ripple preview support to the MLX runner (#19592)

2026-11-07 16:36:53 -08:00

verify.go

…