Skip to content

Actions: RL-Align/RL-Kernel

Actions

All workflows

Actions

Loading...
Loading

Showing runs from all workflows
2,500+ workflow runs
2,500+ 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
feat(ppo): add Qwen3 BF16 adapters and vLLM TP qualification WS1-chain-NPU #235: Pull request #548 synchronize by fusheng-ji
6s fusheng-ji:feat/issue-44-tp-ppo
fusheng-ji:feat/issue-44-tp-ppo
6s
feat(ppo): add Qwen3 BF16 adapters and vLLM TP qualification CI-Pipeline #1305: Pull request #548 synchronize by fusheng-ji
4m 17s fusheng-ji:feat/issue-44-tp-ppo
fusheng-ji:feat/issue-44-tp-ppo
4m 17s
feat(ppo): add Qwen3 BF16 adapters and vLLM TP qualification WS1-chain-GPU #632: Pull request #548 synchronize by fusheng-ji
5s fusheng-ji:feat/issue-44-tp-ppo
fusheng-ji:feat/issue-44-tp-ppo
5s
feat(ppo): add Qwen3 BF16 adapters and vLLM TP qualification GPU CI #953: Pull request #548 synchronize by fusheng-ji
2s
2s
[WS1][CUDA][Qwen3-Next] Batch-invariance matrix for the full model, 97/97 cells bitwise (RFC #428 stack 8/8) CI-Pipeline #1304: Pull request #544 synchronize by fusheng-ji
4m 24s fusheng-ji:feat/ws1-qwen3-next-batch-invariance-ci
fusheng-ji:feat/ws1-qwen3-next-batch-invariance-ci
4m 24s
[WS1][CUDA][Qwen3-Next] Batch-invariance matrix for the full model, 97/97 cells bitwise (RFC #428 stack 8/8) WS1-gtest-GPU #210: Pull request #544 synchronize by fusheng-ji
2s fusheng-ji:feat/ws1-qwen3-next-batch-invariance-ci
fusheng-ji:feat/ws1-qwen3-next-batch-invariance-ci
2s
[WS1][CUDA][Qwen3-Next] Batch-invariance matrix for the full model, 97/97 cells bitwise (RFC #428 stack 8/8) Qwen3-Next-provider-GPU #29: Pull request #544 synchronize by fusheng-ji
7s fusheng-ji:feat/ws1-qwen3-next-batch-invariance-ci
fusheng-ji:feat/ws1-qwen3-next-batch-invariance-ci
7s
[WS1][CUDA][Qwen3-Next] Full-model chain: vLLM rollout vs VIME recompute, raw-bit through two updates and a reload (RFC #428 stack 7/8) WS1-gtest-GPU #209: Pull request #543 synchronize by fusheng-ji
1s fusheng-ji:feat/ws1-qwen3-next-full-model-chain
fusheng-ji:feat/ws1-qwen3-next-full-model-chain
1s
[WS1][CUDA][Qwen3-Next] Full-model chain: vLLM rollout vs VIME recompute, raw-bit through two updates and a reload (RFC #428 stack 7/8) CI-Pipeline #1303: Pull request #543 synchronize by fusheng-ji
4m 20s fusheng-ji:feat/ws1-qwen3-next-full-model-chain
fusheng-ji:feat/ws1-qwen3-next-full-model-chain
4m 20s
[WS1][CUDA][Qwen3-Next] Full-model chain: vLLM rollout vs VIME recompute, raw-bit through two updates and a reload (RFC #428 stack 7/8) Qwen3-Next-provider-GPU #28: Pull request #543 synchronize by fusheng-ji
5s fusheng-ji:feat/ws1-qwen3-next-full-model-chain
fusheng-ji:feat/ws1-qwen3-next-full-model-chain
5s
feat(ppo): add Qwen3 BF16 adapters and vLLM TP qualification WS1-chain-GPU #631: Pull request #548 synchronize by fusheng-ji
5s fusheng-ji:feat/issue-44-tp-ppo
fusheng-ji:feat/issue-44-tp-ppo
5s
feat(ppo): add Qwen3 BF16 adapters and vLLM TP qualification CI-Pipeline #1302: Pull request #548 synchronize by fusheng-ji
3m 47s fusheng-ji:feat/issue-44-tp-ppo
fusheng-ji:feat/issue-44-tp-ppo
3m 47s
feat(ppo): add Qwen3 BF16 adapters and vLLM TP qualification WS1-chain-NPU #234: Pull request #548 synchronize by fusheng-ji
5s fusheng-ji:feat/issue-44-tp-ppo
fusheng-ji:feat/issue-44-tp-ppo
5s
feat(ppo): add Qwen3 BF16 adapters and vLLM TP qualification GPU CI #952: Pull request #548 synchronize by fusheng-ji
1s
1s
feat(h3): extend block validation to full-model and generation qualification CI-Pipeline #1301: Pull request #539 synchronize by fusheng-ji
4m 40s fusheng-ji:feat/h3-one-block
fusheng-ji:feat/h3-one-block
4m 40s
feat(h3): extend block validation to full-model and generation qualification CI-Pipeline #1300: Pull request #539 synchronize by fusheng-ji
4m 14s fusheng-ji:feat/h3-one-block
fusheng-ji:feat/h3-one-block
4m 14s
feat(ppo): add Qwen3 BF16 adapters and vLLM TP qualification WS1-chain-NPU #233: Pull request #548 synchronize by fusheng-ji
7s fusheng-ji:feat/issue-44-tp-ppo
fusheng-ji:feat/issue-44-tp-ppo
7s
feat(ppo): add Qwen3 BF16 adapters and vLLM TP qualification CI-Pipeline #1299: Pull request #548 synchronize by fusheng-ji
3m 48s fusheng-ji:feat/issue-44-tp-ppo
fusheng-ji:feat/issue-44-tp-ppo
3m 48s
feat(ppo): add Qwen3 BF16 adapters and vLLM TP qualification WS1-chain-GPU #630: Pull request #548 synchronize by fusheng-ji
6s fusheng-ji:feat/issue-44-tp-ppo
fusheng-ji:feat/issue-44-tp-ppo
6s
feat(ppo): add Qwen3 BF16 adapters and vLLM TP qualification GPU CI #951: Pull request #548 synchronize by fusheng-ji
1s
1s
feat(h3): extend block validation to full-model and generation qualification CI-Pipeline #1298: Pull request #539 synchronize by fusheng-ji
4m 21s fusheng-ji:feat/h3-one-block
fusheng-ji:feat/h3-one-block
4m 21s
feat(ppo): add Qwen3 BF16 adapters and vLLM TP qualification WS1-chain-GPU #629: Pull request #548 synchronize by fusheng-ji
6s fusheng-ji:feat/issue-44-tp-ppo
fusheng-ji:feat/issue-44-tp-ppo
6s
feat(ppo): add Qwen3 BF16 adapters and vLLM TP qualification CI-Pipeline #1297: Pull request #548 synchronize by fusheng-ji
2m 58s fusheng-ji:feat/issue-44-tp-ppo
fusheng-ji:feat/issue-44-tp-ppo
2m 58s
feat(ppo): add Qwen3 BF16 adapters and vLLM TP qualification WS1-chain-NPU #232: Pull request #548 synchronize by fusheng-ji
6s fusheng-ji:feat/issue-44-tp-ppo
fusheng-ji:feat/issue-44-tp-ppo
6s
feat(ppo): add Qwen3 BF16 adapters and vLLM TP qualification GPU CI #950: Pull request #548 synchronize by fusheng-ji
10s
10s