Skip to content

Actions: huggingface/trl

Actions

Build PR Documentation

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
build_pr_documentation.yml
5,221 workflow runs
5,221 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

Fix: ignore precompute_ref_log_probs when use_liger_loss=True Build PR Documentation #10639: Pull request #4008 synchronize by ginkyenglee
Action required ginkyenglee:feat/disable-precompute-on-liger
ginkyenglee:feat/disable-precompute-on-liger
Action required
🐯 fix: use_liger_kernel with IterableDataset Build PR Documentation #10638: Pull request #4087 synchronize by qgallouedec
Action required jue-jue-zi:main
jue-jue-zi:main
Action required
🐯 fix: use_liger_kernel with IterableDataset Build PR Documentation #10637: Pull request #4087 synchronize by qgallouedec
Action required jue-jue-zi:main
jue-jue-zi:main
Action required
😴 Add vllm_enable_sleep_mode to RLOO Trainer Build PR Documentation #10636: Pull request #4107 synchronize by qgallouedec
4m 14s rloo-vllm-sleep-mode
rloo-vllm-sleep-mode
4m 14s
😴 Add vllm_enable_sleep_mode to RLOO Trainer Build PR Documentation #10635: Pull request #4107 synchronize by qgallouedec
20s rloo-vllm-sleep-mode
rloo-vllm-sleep-mode
20s
update guided decoding param to structured outputs Build PR Documentation #10634: Pull request #4117 synchronize by jiqing-feng
Action required jiqing-feng:param
jiqing-feng:param
Action required
Multi-turn tool calling support Build PR Documentation #10633: Pull request #4115 synchronize by qgallouedec
Skipped multi-turn
multi-turn
Skipped
👋 Remove backend parameter from GuidedDecodingParams Build PR Documentation #10632: Pull request #4123 synchronize by qgallouedec
3m 46s rm-backend-vllm
rm-backend-vllm
3m 46s
📌 Pin vLLM version Build PR Documentation #10631: Pull request #4122 synchronize by qgallouedec
3m 15s pin-vllm
pin-vllm
3m 15s
😷 Refactor GRPO to isolate _generate Build PR Documentation #10630: Pull request #4114 synchronize by qgallouedec
3m 7s generate-method
generate-method
3m 7s
😷 Refactor GRPO to isolate _generate Build PR Documentation #10629: Pull request #4114 synchronize by qgallouedec
3m 50s generate-method
generate-method
3m 50s
📽 Multi image support for GRPO/RLOO Build PR Documentation #10628: Pull request #4113 synchronize by qgallouedec
3m 13s multi-image-support
multi-image-support
3m 13s
📽 Multi image support for GRPO/RLOO Build PR Documentation #10627: Pull request #4113 synchronize by qgallouedec
3m 35s multi-image-support
multi-image-support
3m 35s
📽 Multi image support for GRPO/RLOO Build PR Documentation #10626: Pull request #4113 synchronize by qgallouedec
4m 33s multi-image-support
multi-image-support
4m 33s
😴 Add vllm_enable_sleep_mode to RLOO Trainer Build PR Documentation #10625: Pull request #4107 synchronize by qgallouedec
4m 15s rloo-vllm-sleep-mode
rloo-vllm-sleep-mode
4m 15s
📽 Multi image support for GRPO/RLOO Build PR Documentation #10624: Pull request #4113 synchronize by qgallouedec
3m 2s multi-image-support
multi-image-support
3m 2s
👋 Remove backend parameter from GuidedDecodingParams Build PR Documentation #10623: Pull request #4123 opened by qgallouedec
3m 17s rm-backend-vllm
rm-backend-vllm
3m 17s
📽 Multi image support for GRPO/RLOO Build PR Documentation #10622: Pull request #4113 synchronize by qgallouedec
4m 5s multi-image-support
multi-image-support
4m 5s
🟩 Drop image_split_sizes in favour of image_grid_thw Build PR Documentation #10621: Pull request #4111 synchronize by qgallouedec
3m 17s drop-image_split_sizes
drop-image_split_sizes
3m 17s
📌 Pin vLLM version Build PR Documentation #10620: Pull request #4122 synchronize by qgallouedec
3m 51s pin-vllm
pin-vllm
3m 51s
📌 Pin vLLM version Build PR Documentation #10619: Pull request #4122 opened by qgallouedec
2m 36s pin-vllm
pin-vllm
2m 36s
[GRPO] Ensure max_prompt_length can accommodate protected tokens Build PR Documentation #10618: Pull request #4121 opened by kashif
3m 26s internvl-grpo-issue-4061
internvl-grpo-issue-4061
3m 26s
🔭 Align param passing to VLM configs in generate_tiny_models Build PR Documentation #10617: Pull request #4118 synchronize by qgallouedec
3m 30s albertvillanova:fu-4101
albertvillanova:fu-4101
3m 30s
🎁 RewardTrainer refactor Build PR Documentation #10616: Pull request #4093 synchronize by qgallouedec
4m 2s reward-refactor
reward-refactor
4m 2s
🎞️ Support sequence classification models in clone_chat_template Build PR Documentation #10615: Pull request #4097 synchronize by qgallouedec
3m 55s support-seq-cls-clone-chat
support-seq-cls-clone-chat
3m 55s