CERBERUS/ollama
1
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-09-01 00:45:30 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions
ollama/x/mlxrunner
History
Exact
Jesse Gross 3b96a8972a mlx: remove the text-only gemma3 model 
The MLX gemma3 port implements only the text stack, while gemma3 as GGUF
runs on llama-server with vision. Once MLX takes priority for
architectures both engines support, a registered gemma3 would route the
model to the engine that cannot serve images. No gemma3 safetensors
manifests were ever published, so removing the architecture affects no
existing installs and keeps gemma3 on llama-server.
2026-08-26 14:01:50 -07:00
..
batch mlxrunner: feed media features to the model during prefill 2026-08-09 10:37:05 -07:00
cache mlxrunner: stop cache rewind refills from corrupting later lazy snapshots 2026-08-05 16:31:56 -07:00
mlx MLX: Qwen3.8 Flash Next support (#18032) 2026-08-26 08:05:59 -07:00
model mlxrunner: reject media requests the model cannot serve 2026-08-09 10:37:05 -07:00
sample mlx: return exact types and evaluate arrays in the value readers 2026-08-25 17:14:23 -07:00
xgrammar mlxrunner: add structured output support 2026-08-25 17:14:23 -07:00
cache_trie.go mlxrunner: grow the prefix trie by whole child nodes so restore points survive resumed prefills 2026-08-21 09:58:33 -07:00
cache_trie_test.go mlxrunner: grow the prefix trie by whole child nodes so restore points survive resumed prefills 2026-08-21 09:58:33 -07:00
client.go mlxrunner: add structured output support 2026-08-25 17:14:23 -07:00
dflash.go mlxrunner: feed media features to the model during prefill 2026-08-09 10:37:05 -07:00
dflash_test.go mlxrunner: add structured output support 2026-08-25 17:14:23 -07:00
grammar.go mlxrunner: add structured output support 2026-08-25 17:14:23 -07:00
grammar_mask_test.go mlxrunner: add structured output support 2026-08-25 17:14:23 -07:00
grammar_test.go mlxrunner: add structured output support 2026-08-25 17:14:23 -07:00
imports.go mlx: remove the text-only gemma3 model 2026-08-26 14:01:50 -07:00
media.go mlxrunner: feed media features to the model during prefill 2026-08-09 10:37:05 -07:00
media_test.go mlxrunner: feed media features to the model during prefill 2026-08-09 10:37:05 -07:00
mtp.go mlxrunner: feed media features to the model during prefill 2026-08-09 10:37:05 -07:00
mtp_test.go mlxrunner: add structured output support 2026-08-25 17:14:23 -07:00
pipeline.go mlxrunner: add structured output support 2026-08-25 17:14:23 -07:00
pipeline_test.go mlxrunner: expand image tags into placeholder tokens 2026-08-09 10:37:05 -07:00
prefix_cache.go mlxrunner: keep prefill snapshots when a request is cancelled mid-prompt 2026-08-21 09:58:33 -07:00
prefix_cache_scenario_test.go mlxrunner: keep prefill snapshots when a request is cancelled mid-prompt 2026-08-21 09:58:33 -07:00
prefix_cache_test.go mlxrunner: keep prefill snapshots when a request is cancelled mid-prompt 2026-08-21 09:58:33 -07:00
runner.go mlxrunner: avoid Metal GPU timeouts when loading models from slow storage 2026-08-25 17:14:56 -07:00
server.go mlxrunner: add structured output support 2026-08-25 17:14:23 -07:00
speculate.go mlxrunner: add structured output support 2026-08-25 17:14:23 -07:00
speculate_depth.go mlxrunner: add a block-diffusion drafting session 2026-08-07 19:33:35 -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: add a block-diffusion drafting session 2026-08-07 19:33:35 -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