ollama/x/mlxrunner
Daniel Hiltgen 7926b99e0e
mlx: bump dependency (#16935)
Update MLX to 548dd80.

Fix direct MLX tests to run on pinned MLX threads so test execution matches the runner's MLX thread-affinity model.
2026-06-29 09:39:11 -07:00
..
batch mlxrunner: support draft heads that maintain draft caches 2026-06-22 15:25:45 -07:00
cache mlxrunner: drive MTP speculation through cache snapshots 2026-06-09 00:39:19 -07:00
mlx mlx: bump dependency (#16935) 2026-06-29 09:39:11 -07:00
model mlxrunner: choose the speculative draft length to maximize throughput 2026-06-22 15:25:45 -07:00
sample mlxrunner: apply in-flight drafts to proposal penalty history 2026-06-22 15:25:45 -07:00
cache.go mlxrunner: capture prefill snapshots across the forward 2026-06-09 00:39:19 -07:00
cache_test.go mlxrunner: capture prefill snapshots across the forward 2026-06-09 00:39:19 -07:00
cache_trie.go mlxrunner: drive MTP speculation through cache snapshots 2026-06-09 00:39:19 -07:00
cache_trie_test.go mlxrunner: share KV cache across conversations with common prefixes 2026-03-18 16:06:33 -07:00
client.go MLX: wire up scheduler selected context size for ps (#16918) 2026-06-26 08:47:03 -07:00
imports.go models: add cohere2_moe (Command A / North) to the MLX engine (#16670) 2026-06-16 23:15:21 -07:00
mtp.go mlxrunner: choose the speculative draft length to maximize throughput 2026-06-22 15:25:45 -07:00
mtp_test.go mlxrunner: choose the speculative draft length to maximize throughput 2026-06-22 15:25:45 -07:00
pipeline.go mlxrunner: choose the speculative draft length to maximize throughput 2026-06-22 15:25:45 -07:00
runner.go mlxrunner: support draft heads that maintain draft caches 2026-06-22 15:25:45 -07:00
server.go mlx: rework the MLX sampler (#16122) 2026-05-13 17:18:27 -07:00
speculate.go mlxrunner: choose the speculative draft length to maximize throughput 2026-06-22 15:25:45 -07:00
speculate_depth.go mlxrunner: choose the speculative draft length to maximize throughput 2026-06-22 15:25:45 -07:00
speculate_depth_test.go mlxrunner: choose the speculative draft length to maximize throughput 2026-06-22 15:25:45 -07:00
speculate_stats.go mlxrunner: choose the speculative draft length to maximize throughput 2026-06-22 15:25:45 -07:00
status_memory.go mlx: avoid status timeout during inference (#16086) 2026-05-11 16:03:38 -07:00
status_memory_test.go mlx: avoid status timeout during inference (#16086) 2026-05-11 16:03:38 -07:00
utf8_buffer.go consolidate the tokenizer (#14327) 2026-02-19 15:55:45 -08:00
utf8_buffer_test.go consolidate the tokenizer (#14327) 2026-02-19 15:55:45 -08:00