Skip to content

Actions: ml-explore/mlx-lm

Actions

All workflows

Actions

Loading...
Loading

Showing runs from all workflows
789 workflow runs
789 workflow runs

Filter by Workflow

⌥ + click/return to exclude

Filter by Event

⌥ + click/return to exclude

Filter by Status

⌥ + click/return to exclude

Filter by Branch

⌥ + click/return to exclude

Filter by Actor

⌥ + click/return to exclude
Add DeepSeek-v4 (Flash/Pro) Build and Test #1267: Pull request #1192 synchronize by Blaizzy
Action required Blaizzy:pc/add-deepseekv4flash-model
Blaizzy:pc/add-deepseekv4flash-model
Action required
Add DeepSeek-v4 (Flash/Pro) Build and Test #1266: Pull request #1192 synchronize by Blaizzy
Action required Blaizzy:pc/add-deepseekv4flash-model
Blaizzy:pc/add-deepseekv4flash-model
Action required
Add DeepSeek-v4 (Flash/Pro) Build and Test #1265: Pull request #1192 synchronize by Blaizzy
Action required Blaizzy:pc/add-deepseekv4flash-model
Blaizzy:pc/add-deepseekv4flash-model
Action required
fix(gemma4): drop KV-shared layer projections in sanitize Build and Test #1264: Pull request #1205 opened by Fox13
Action required Fox13:fix/gemma4-kv-shared-sanitize
Fox13:fix/gemma4-kv-shared-sanitize
Action required
minimax: validate head_dim against checkpoint, drop unused shared_intermediate_size Build and Test #1263: Pull request #1204 opened by adurham
Action required adurham:minimax-validate-head-dim
adurham:minimax-validate-head-dim
Action required
Add TurboQuantKVCache: 3-bit/4-bit KV cache compression for generation Build and Test #1262: Pull request #1202 opened by dedalien
Action required dedalien:turboq/integrate-generic-quant-sdpa
dedalien:turboq/integrate-generic-quant-sdpa
Action required
Add DeepSeek-V4 (Flash) model support Build and Test #1261: Pull request #1201 synchronize by akashgoswami
Action required akashgoswami:add-deepseek-v4
akashgoswami:add-deepseek-v4
Action required
Add DeepSeek-v4 (Flash/Pro) Build and Test #1260: Pull request #1192 synchronize by Blaizzy
Action required Blaizzy:pc/add-deepseekv4flash-model
Blaizzy:pc/add-deepseekv4flash-model
Action required
Add DeepSeek-v4 (Flash/Pro) Build and Test #1259: Pull request #1192 synchronize by Blaizzy
Action required Blaizzy:pc/add-deepseekv4flash-model
Blaizzy:pc/add-deepseekv4flash-model
Action required
Add DeepSeek-v4 (Flash/Pro) Build and Test #1258: Pull request #1192 synchronize by Blaizzy
Action required Blaizzy:pc/add-deepseekv4flash-model
Blaizzy:pc/add-deepseekv4flash-model
Action required
Add DeepSeek-v4 (Flash/Pro) Build and Test #1257: Pull request #1192 synchronize by Blaizzy
Action required Blaizzy:pc/add-deepseekv4flash-model
Blaizzy:pc/add-deepseekv4flash-model
Action required
Add DeepSeek-V4 (Flash) model support Build and Test #1256: Pull request #1201 opened by akashgoswami
Action required akashgoswami:add-deepseek-v4
akashgoswami:add-deepseek-v4
Action required
Add --q-override for per-layer quantization Build and Test #1255: Pull request #922 synchronize by spicyneuron
Action required spicyneuron:override
spicyneuron:override
Action required
Add DeepSeek-v4 (Flash/Pro) Build and Test #1254: Pull request #1192 synchronize by Blaizzy
Action required Blaizzy:pc/add-deepseekv4flash-model
Blaizzy:pc/add-deepseekv4flash-model
Action required
feat: add DeepSeek-V4 (Pro/Flash) model support Build and Test #1253: Pull request #1189 synchronize by machiabeli
Action required machiabeli:feat/deepseek-v4
machiabeli:feat/deepseek-v4
Action required
feat: native MTP speculative decoding for qwen3_5_moe (Qwen3.5-3.6) Build and Test #1252: Pull request #990 synchronize by AirRunner
Action required AirRunner:feat/mtp-native
AirRunner:feat/mtp-native
Action required
Add DeepSeek-v4 (Flash/Pro) Build and Test #1251: Pull request #1192 synchronize by Blaizzy
Action required Blaizzy:pc/add-deepseekv4flash-model
Blaizzy:pc/add-deepseekv4flash-model
Action required
Add dense qwen3_5 support for learned quantization Build and Test #1250: Pull request #1200 opened by iamwavecut
Action required iamwavecut:research/qwen3-5-quant-lab
iamwavecut:research/qwen3-5-quant-lab
Action required
feat: add DeepSeek-V4 (Pro/Flash) model support Build and Test #1249: Pull request #1189 synchronize by machiabeli
Action required machiabeli:feat/deepseek-v4
machiabeli:feat/deepseek-v4
Action required
Add DeepSeek-v4 (Flash/Pro) Build and Test #1248: Pull request #1192 synchronize by Blaizzy
Action required Blaizzy:pc/add-deepseekv4flash-model
Blaizzy:pc/add-deepseekv4flash-model
Action required
Add EngGPT MoE model support Build and Test #1247: Pull request #1199 opened by robertobissanti
Action required robertobissanti:add-enggpt-moe
robertobissanti:add-enggpt-moe
Action required
Add DeepSeek-v4 (Flash/Pro) Build and Test #1246: Pull request #1192 synchronize by Blaizzy
Action required Blaizzy:pc/add-deepseekv4flash-model
Blaizzy:pc/add-deepseekv4flash-model
Action required
feat: native MTP speculative decoding for qwen3_5_moe (Qwen3.5-3.6) Build and Test #1245: Pull request #990 synchronize by AirRunner
Action required AirRunner:feat/mtp-native
AirRunner:feat/mtp-native
Action required
Add DeepSeek-v4 (Flash/Pro) Build and Test #1244: Pull request #1192 synchronize by Blaizzy
Action required Blaizzy:pc/add-deepseekv4flash-model
Blaizzy:pc/add-deepseekv4flash-model
Action required
feat: native MTP speculative decoding for qwen3_5_moe (Qwen3.5-3.6) Build and Test #1243: Pull request #990 synchronize by AirRunner
Action required AirRunner:feat/mtp-native
AirRunner:feat/mtp-native
Action required