Skip to content

Actions: THUDM/slime

Actions

pre-commit

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
pre-commit.yml
2,500+ workflow runs
2,500+ workflow runs

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
[Fix] Support origin HF weight backfilling in parallel converter pre-commit #4794: Pull request #2270 opened by albaNnaksqr
1m 15s albaNnaksqr:fix/parallel-add-missing-weights
albaNnaksqr:fix/parallel-add-missing-weights
1m 15s
Fix O(#segments) per-comm memory probe that slows weight sync & training under expandable_segments pre-commit #4793: Pull request #2269 synchronize by yszhli
1m 17s yszhli:fix/per-comm-memory-probe-perf
yszhli:fix/per-comm-memory-probe-perf
1m 17s
Fix O(#segments) per-comm memory probe that slows weight sync & training under expandable_segments pre-commit #4792: Pull request #2269 opened by yszhli
2m 4s yszhli:fix/per-comm-memory-probe-perf
yszhli:fix/per-comm-memory-probe-perf
2m 4s
Fix model convert when use latest megatron pre-commit #4791: Pull request #2267 opened by alexqdh
48s alexqdh:fix_model_convert_use_latest_megatron
alexqdh:fix_model_convert_use_latest_megatron
48s
Refactor --save-debug-train-data (#2266) pre-commit #4790: Commit 681b3ad pushed by zhuzilin
1m 32s main
main
1m 32s
Refactor --save-debug-train-data pre-commit #4789: Pull request #2266 opened by zhuzilin
1m 9s zilin/save_debug_train_darta
zilin/save_debug_train_darta
1m 9s
fix(npu): bracket IPv6 hosts in distributed init methods (#2199) pre-commit #4788: Commit d38dc29 pushed by zhuzilin
1m 17s main
main
1m 17s
[DON'T MERGE] run CI pre-commit #4787: Pull request #2053 synchronize by zhuzilin
1m 12s zilin/ci-dont-merge
zilin/ci-dont-merge
1m 12s
fix: honor every eval.defaults key and restore per-dataset stop / min… pre-commit #4786: Commit d3c0e79 pushed by zhuzilin
1m 22s main
main
1m 22s
fix: honor every eval.defaults key and restore per-dataset stop / min_new_tokens pre-commit #4785: Pull request #2242 synchronize by zhuzilin
1m 6s keepkeen:fix/eval-defaults-dropped-keys
keepkeen:fix/eval-defaults-dropped-keys
1m 6s
fix: stop the fully-async rollout dropping completed groups (#2238) pre-commit #4784: Commit 7e02052 pushed by zhuzilin
1m 11s main
main
1m 11s
Fix tau-bench token deltas for reasoning templates (#2213) pre-commit #4783: Commit fb393e5 pushed by zhuzilin
1m 12s main
main
1m 12s
fix: don't overwrite an explicitly set --start-rollout-id (#2236) pre-commit #4782: Commit b91f59e pushed by zhuzilin
1m 23s main
main
1m 23s
fix: whiten advantages over the DP group that includes context parall… pre-commit #4781: Commit dd7f037 pushed by zhuzilin
1m 11s main
main
1m 11s
fix: pair --log-correct-samples rewards with the DP-local samples (#2… pre-commit #4780: Commit c1dd9ab pushed by zhuzilin
1m 23s main
main
1m 23s
fix: pair --log-correct-samples rewards with the DP-local samples pre-commit #4779: Pull request #2234 synchronize by zhuzilin
1m 31s keepkeen:fix/log-correct-samples-dp-partition
keepkeen:fix/log-correct-samples-dp-partition
1m 31s
fix: clear exec_and_wait's spawn lock between logical invocations (#2… pre-commit #4778: Commit fcbd428 pushed by zhuzilin
1m 19s main
main
1m 19s
fix: restore args.ckpt_step after load_other_checkpoint (#2243) pre-commit #4777: Commit 68a7347 pushed by zhuzilin
1m 24s main
main
1m 24s
Fix placement group crash for external engines under debug_rollout_on… pre-commit #4776: Commit 916b33a pushed by zhuzilin
1m 29s main
main
1m 29s
Fix placement group crash for external engines under debug_rollout_only pre-commit #4775: Pull request #2170 synchronize by zhuzilin
1m 27s coding-famer:fix/rolloutonly
coding-famer:fix/rolloutonly
1m 27s
fix(mtp): support multi-head MTP loss logging (mtp-num-layers > 1) (#… pre-commit #4774: Commit aed9321 pushed by zhuzilin
1m 14s main
main
1m 14s
[Doc] Clarify PPO/Critic docs after #1856 (#2189) pre-commit #4773: Commit 3b3bce8 pushed by zhuzilin
1m 22s main
main
1m 22s
docs(examples): list coding_agent_rl in examples/README (#2133) pre-commit #4772: Commit 19abf05 pushed by zhuzilin
1m 7s main
main
1m 7s
docs(readme): add Dressage to Chinese ecosystem (#2138) pre-commit #4771: Commit fb735f1 pushed by zhuzilin
1m 8s main
main
1m 8s
perf: vectorize REINFORCE++ discounted returns (#2205) pre-commit #4770: Commit 2c6323b pushed by zhuzilin
1m 32s main
main
1m 32s