Refactor: consolidate DSpark decode output projection - #945
zhangqi-chen merged 1 commit into
Conversation
|
No actionable comments were generated in the recent review. 🎉 ℹ️ Recent review info⚙️ Run configurationConfiguration used: Organization UI Review profile: CHILL Plan: Pro Plus Run ID: 📒 Files selected for processing (3)
📝 WalkthroughWalkthroughThe decode path now uses TP-based DSA-CP collectives and sharded O-projection naming. Configuration adds token-owner and output-weight shard constants. Collective dimensions, synchronization, fixture wiring, golden data, kernels, and tests use the new terminology. ChangesDSA-CP TP migration
Estimated code review effort: 4 (Complex) | ~45 minutes Possibly related PRs
Poem
🚥 Pre-merge checks | ✅ 4 | ❌ 1❌ Failed checks (1 warning)
✅ Passed checks (4 passed)
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
| DP = 4 # DP groups per node | ||
| EP = 16 # expert-parallel world size (moe overrides it from --ep) | ||
| TP = 4 # ranks in the model-sharding group for each DP rank | ||
| TOKEN_OWNER_COUNT = TP # the same ranks own disjoint decode-token rows |
There was a problem hiding this comment.
remove this line, keep only tp dp ep
| # Per-component TP degree, over the components that shard. | ||
| TP_Q_B = 1 # wq_b: replicated across the DSA-CP group | ||
| TP_O_A = TP # wo_a: ColumnParallel over o_groups |
| # ----------------------------------------------------------------------------------------------------------- | ||
| # ci: devices=4 | ||
| """DeepSeek-V4 decode DSA-CP communication and grouped output-projection layouts.""" | ||
| """Collectives for the DeepSeek-V4 decode DSA-CP layout on one TP group.""" |
There was a problem hiding this comment.
never mention dsa-cp, which is a vllm config
| # See LICENSE in the root of the software repository for the full text of the License. | ||
| # ----------------------------------------------------------------------------------------------------------- | ||
| """DeepSeek-V4 decode DSA-CP receive-side grouped output projection.""" | ||
| """DeepSeek-V4 decode TP-sharded grouped output projection.""" |
There was a problem hiding this comment.
rename this file to decode_o_proj.py, move dsa_cp_collectives into this file, and also oproj(tp=1) in 3 attentions.
| # See LICENSE in the root of the software repository for the full text of the License. | ||
| # ----------------------------------------------------------------------------------------------------------- | ||
| # ci: devices=4 | ||
| """DeepSeek-V4 decode DSA-CP communication and grouped output-projection layouts.""" |
There was a problem hiding this comment.
delete this file, merge into decode_o_proj.py
| @@ -7,18 +7,25 @@ | |||
| # See LICENSE in the root of the software repository for the full text of the License. | |||
There was a problem hiding this comment.
delete this file, merge into decode_o_proj.py
9e2b5e0 to
0af34a9
Compare
- Keep decode parallel configuration limited to TP, DP, and EP - Consolidate attention collectives and TP-sharded output projection in decode_o_proj.py
0af34a9 to
ffdb27b
Compare
in decode_o_proj.py