feat(agentx): add Kimi-K3 FP4 MI355X ATOM DSpark recipe - #2670
Open
zejunchen-zejun wants to merge 6 commits into
Open
feat(agentx): add Kimi-K3 FP4 MI355X ATOM DSpark recipe#2670zejunchen-zejun wants to merge 6 commits into
zejunchen-zejun wants to merge 6 commits into
Conversation
Adds the MI355X Kimi-K3 ATOM AgentX submission alongside the existing vLLM arm: same checkpoint, same runner, same concurrency points, so the two engines are directly comparable. TP8 at concurrency 1 and 4 is GPU-resident. Concurrency 8 and 10 switch on the LMCache DRAM tier and ATOM's CPU state-offload tier together, because Kimi-K3 is a hybrid -- Kimi Delta Attention carries a per-request recurrent state alongside the paged KV, so a resumed agentic turn needs the state back and the paged KV tier alone cannot restore one. spec-decode-acceptance-rate is derived from the committed golden acceptance length 2.51 at num_speculative_tokens 2 as (2.51 - 1) / 2 = 0.755, the same golden the vLLM arm feeds to synthetic_acceptance_length, so both engines are held to one acceptance assumption. LMCACHE_MAX_LOCAL_CPU_SIZE is per rank, so the aggregate TOTAL_CPU_DRAM_GB is divided by TP as the agentic README requires; dram-utilization 0.085 lands that at roughly 32 GB per rank. 新增 MI355X 上 Kimi-K3 的 ATOM AgentX 提交，与既有 vLLM 分支并列：相同权重、 相同 runner、相同并发点，两个引擎可直接对比。 TP8 在并发 1 和 4 下全部驻留 GPU。并发 8 和 10 同时开启 LMCache DRAM 层与 ATOM 的 CPU state-offload 层，因为 Kimi-K3 是混合架构——Kimi Delta Attention 在分页 KV 之外还带有每请求的循环状态，恢复一次 agentic 轮次必须取回该状态， 仅靠分页 KV 层无法还原。 spec-decode-acceptance-rate 由仓库内已提交的 golden 接受长度 2.51（ num_speculative_tokens 为 2）按 (2.51 - 1) / 2 = 0.755 推导，与 vLLM 分支传给 synthetic_acceptance_length 的 golden 一致，使两个引擎处于同一接受假设下。 LMCACHE_MAX_LOCAL_CPU_SIZE 是每 rank 的设置，因此按 agentic README 的要求将 聚合预算 TOTAL_CPU_DRAM_GB 除以 TP；dram-utilization 取 0.085 使其落在每 rank 约 32 GB。 Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
A mechanical dry-run diff of the resolved server command against the ATOM recipe, per concurrency, turned up three gaps: - AITER_LOG_LEVEL was missing. ATOM requires it: without it the aiter kernel logs flood the server log for the whole 3600 s replay. - dram-utilization 0.085 gave an aggregate of 254 GB, which floors to 31 GB per rank after the divide-by-TP. 0.086 gives 257 and lands on exactly the 32 GB per rank the recipe was measured with. - OFFLOAD_PROFILE stays unset, matching the measured runs rather than the recipe's 1; it only enables per-step offload statistics. Now stated in the script so the difference reads as a choice, not an omission. After this the two commands are identical on every server flag and every environment variable at concurrency 1, 4, 8 and 10. The one remaining textual difference is an explicit --host 0.0.0.0, which is a no-op: ATOM's DEFAULT_HOST is already 0.0.0.0. 按并发逐档对 resolved server command 与 ATOM recipe 做了机械化 dry-run 比对， 发现三处差异： - 缺少 AITER_LOG_LEVEL。ATOM 要求设置该变量，否则 aiter kernel 日志会在整个 3600 秒回放期间刷屏。 - dram-utilization 取 0.085 时聚合预算为 254 GB，按 TP 整除后落到每 rank 31 GB。改为 0.086 得到 257，整除后正好是 recipe 实测所用的每 rank 32 GB。 - OFFLOAD_PROFILE 保持不设置，与实测运行一致，而非 recipe 中的 1；该变量仅 开启逐步的 offload 统计。现已在脚本中写明，使该差异体现为有意选择而非遗漏。 此后两侧命令在并发 1、4、8、10 下的每一个服务端参数与每一个环境变量上完全一致。 唯一残留的文本差异是显式的 --host 0.0.0.0，而这是空操作：ATOM 的 DEFAULT_HOST 本身就是 0.0.0.0。 Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
zejunchen-zejun
marked this pull request as ready for review
August 19, 2026 07:25
zejunchen-zejun
requested review from
1am9trash,
billishyahao,
chunfangamd,
seungrokj and
yctseng0211
as code owners
August 19, 2026 07:25
![claude[bot]](https://avatars.githubusercontent.com/in/1236702?s=60&v=4){kind=small}
Contributor
|
Dispatched trusted sweep run for approved external revision 已为获批的外部提交 |
Contributor
|
Dispatched trusted sweep run for approved external revision 已为获批的外部提交 |
Contributor
|
Dispatched trusted sweep run for approved external revision 已为获批的外部提交 |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Recipe PR: ROCm/ATOM#1941
Adds the MI355X Kimi-K3 ATOM AgentX submission alongside the existing vLLM arm: same checkpoint, same runner, same concurrency points, so the two engines are directly comparable.
TP8 at concurrency 1 and 4 is GPU-resident. Concurrency 8 and 10 switch on the LMCache DRAM tier and ATOM's CPU state-offload tier together, because Kimi-K3 is a hybrid -- Kimi Delta Attention carries a per-request recurrent state alongside the paged KV, so a resumed agentic turn needs the state back and the paged KV tier alone cannot restore one.
spec-decode-acceptance-rate is derived from the committed golden acceptance length 2.51 at num_speculative_tokens 2 as (2.51 - 1) / 2 = 0.755, the same golden the vLLM arm feeds to synthetic_acceptance_length, so both engines are held to one acceptance assumption.
LMCACHE_MAX_LOCAL_CPU_SIZE is per rank, so the aggregate TOTAL_CPU_DRAM_GB is divided by TP as the agentic README requires; dram-utilization 0.085 lands that at roughly 32 GB per rank.