Skip to content

Pull requests: RL-Align/RL-Kernel

New pull request New
23 Open 56 Closed
23 Open 56 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Reviews
Filter by reviews
No reviews Review required Approved review Changes requested
Assignee
Filter by who’s assigned
Assigned to nobody Loading
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

Add kernel gtest operator checker and used logprob to test gtest
#197 opened Jun 27, 2026 by a-kaa Collaborator Loading…
7
feat(ws1): add NativeKVCacheAttnOp pure-PyTorch KV-cache attention reference
#195 opened Jun 27, 2026 by maxiaosong1124 Collaborator Loading…
7
[FEAT][kernels] route LM-head vocab projection through deterministic GEMM
#194 opened Jun 26, 2026 by inaniloquentee Collaborator Loading…
5
[WS1]feat: add embedding invariance and LM-head linear_logp routing
#190 opened Jun 25, 2026 by inaniloquentee Collaborator Loading…
3
[FEAT][kernels] Add tensor-parallel linear_logp path
#189 opened Jun 24, 2026 by inaniloquentee Collaborator Loading…
16
:feat(ws1): add NativeAttentionOp pure-PyTorch standard-softmax reference
#188 opened Jun 24, 2026 by maxiaosong1124 Collaborator Loading…
13
Add OpenAI-compatible local serving
#183 opened Jun 23, 2026 by haoruilee Contributor Loading…
1
32
feat(kernels): add fused masking + variable-length pack-and-pad op needs-gpu-ci
#182 opened Jun 23, 2026 by Chen-BUPT Loading…
14
[WS2][distributed] Add deterministic all-reduce contract and smoke tests
#181 opened Jun 23, 2026 by CyberSecurityErial Loading…
8
[WS1][kernels] Batch-invariant deterministic GEMM (fwd + bwd) needs-gpu-ci
#180 opened Jun 22, 2026 by Flink-ddd Collaborator Loading…
1
11
feat(ws1):Add LogProb reference operator interface(reuse) needs-gpu-ci
#179 opened Jun 22, 2026 by a-kaa Collaborator Loading…
4
[WIP] [WS1] Add tests to ensure kv cache consistency for prefill & decode
#178 opened Jun 22, 2026 by zhangj1an • Draft
1
3
feat(ws1): NativeLMHeadOp pure-PyTorch ground-truth reference + numerical contract tests needs-gpu-ci
#170 opened Jun 22, 2026 by maxiaosong1124 Collaborator Loading…
9
feat(ws1): NativeEmbeddingOp pure-PyTorch ground-truth reference + numerical contract tests needs-gpu-ci
#169 opened Jun 22, 2026 by maxiaosong1124 Collaborator Loading…
6 tasks done
8
feat(ws1): Add PyTorch matmul reference operator needs-gpu-ci
#168 opened Jun 21, 2026 by a-kaa Collaborator Loading…
6
feat(ws1): Add PyTorch RoPE reference operator needs-gpu-ci
#167 opened Jun 21, 2026 by a-kaa Collaborator Loading…
13
feat(ws1): NativeSiLUOp + NativeSwiGLUOp pure-PyTorch ground-truth references + numerical contract tests needs-gpu-ci
#166 opened Jun 21, 2026 by maxiaosong1124 Collaborator Loading…
6 tasks done
9
feat: add vime rollout logp probe
#142 opened Jun 16, 2026 by inaniloquentee Collaborator Loading…
1
docs: define vime integration design
#126 opened Jun 16, 2026 by inaniloquentee Collaborator Loading…
1
docs: map vime architecture hook points
#125 opened Jun 16, 2026 by inaniloquentee Collaborator Loading…
1
1
feat: add logprob cross-engine benchmark
#107 opened Jun 13, 2026 by inaniloquentee Collaborator Loading…
1
10
feat(testing): add TP-invariant reduction references
#103 opened Jun 12, 2026 by inaniloquentee Collaborator Loading…
1
4
Add batch-invariant deterministic CUDA logp needs-gpu-ci
#98 opened Jun 11, 2026 by inaniloquentee Collaborator Loading…
17
ProTip! Adding no:label will show everything without a label.