[AMD][AgentX] DeepSeek-V4 MI355X agentic disaggregated benchmarking#2170
[AMD][AgentX] DeepSeek-V4 MI355X agentic disaggregated benchmarking#2170ichbinblau wants to merge 40 commits into
Conversation
ichbinblau
requested review from
1am9trash,
billishyahao,
chunfangamd,
seungrokj and
yctseng0211
as code owners
![claude[bot]](https://avatars.githubusercontent.com/in/1236702?s=60&v=4){kind=small}
|
see unofficial run visualizer at https://inferencex.semianalysis.com/inference?unofficialRun=29140974686 |
|
see unofficial run visualizer at https://inferencex.semianalysis.com/inference?unofficialRun=29141073508 |
|
see unofficial run visualizer at https://inferencex.semianalysis.com/inference?unofficialRun=29141213005 |
billishyahao
left a comment
billishyahao
left a comment
There was a problem hiding this comment.
As a PR reviewer and CODEOWNER, I have reviewed this and have:
- Verified that as of the moment of typing this, this is the latest version of PR_REVIEW_CHECKLIST.md
- Verified that the general code quality meets the InferenceX standard and does not make the code quality any worse. Approve for day 0
- Verified that this PR has passed PR validation. Please link to GitHub Action workflow that shows this. https://github.com/SemiAnalysisAI/InferenceX/actions/runs/29141213005
- Verified that this PR passes evals. Please link to GitHub Action workflow that shows this. https://github.com/SemiAnalysisAI/InferenceX/actions/runs/29141213005
- Verified that speculative decoding PRs uses chat templates to align the AL distribution to real world
- Verified that the model architecture isn't changed with benchmark hacks like using --hf-overrides to skipping indexer for every x layers on models that don't natively support this. As a general rule, we won't accept optimizations that reduces the number of model architecture FLOPs. Anything that makes that same computation run faster is fair game; FLOPs at lower precisions is fine, given that the config passes private evals. As an general north star princple, we should only use optimizations which is used in production by customers that care about accuracy
- If an company claims that they support vLLM/SGLang as first class LLM inference engines on their hardware, I have verified that the respective vLLM submission made using upstream https://hub.docker.com/u/vllm docker repo, upstream SGLang https://hub.docker.com/u/lmsysorg docker repo. The only exceptions are for new hardware, such as MI455X UALoE72, Vera Rubin NVL72, Rubin NVL8, etc., and for new model architectures where there is an actual reason why vLLM/SGLang does not fundamentally support them yet as supported by vLLM/SGLang community maintainers
- If an company claims that they support vLLM/SGLang as first class upstream in-tree LLM inference engines on their hardware, I have have verified that the respective vLLM/SGLang submission has been made before additional frameworks (TRT-LLM, ATOM, etc.). The only exceptions are for new hardware, such as MI455X UALoE72, Vera Rubin NVL72, Rubin NVL8, etc., and for new model architectures where there is an actual reason why vLLM/SGLang does not fundamentally support them yet.
- Verified that the single-node recipes are similar to the official vLLM recipes and/or theSGLang cookbook:
- If they are not, I have verified that a PR has been opened in vLLM recipe repo or SGLang repo and linked it below in the additional detail section:
- If any of the above criteria cannot reasonably be satisfied, I have provided additional reasoning below.
Additional detail section:
- insert any additional info here
This is the re-submission of #2127
Signed: @billishyahao
❌❌❌ REJECTED ❌❌❌@billishyahao blocking: no evals ran on the signed-off commit, no authorized ✅ Check 0 (CODEOWNER): PASS — you own |
|
see unofficial run visualizer at https://inferencex.semianalysis.com/inference?unofficialRun=29222483374 |
| # DSV4 uses page-size 256 (set in models.yaml); HiCache must match. | ||
| export HICACHE_PAGE_SIZE="${HICACHE_PAGE_SIZE:-256}" | ||
| # HiCache ratio (host pool = ratio * GPU KV pool). Default derived in server_sglang.sh. | ||
| export HICACHE_RATIO="${HICACHE_RATIO:-}" |
There was a problem hiding this comment.
@cquil11 plz check how this var works and if it follows the rule of ALLOWED_CPU_MEM = amount_of_cpu_mem * (# of gpus used per node / total GPUs per node)
|
see unofficial run visualizer at https://inferencex.semianalysis.com/inference?unofficialRun=29223014792 |
|
see unofficial run visualizer at https://inferencex.semianalysis.com/inference?unofficialRun=29229732720 |
|
see unofficial run visualizer at https://inferencex.semianalysis.com/inference?unofficialRun=29235085283 |
|
see unofficial run visualizer at https://inferencex.semianalysis.com/inference?unofficialRun=29237371210 |
|
see unofficial run visualizer at https://inferencex.semianalysis.com/inference?unofficialRun=29237371210 |
|
see unofficial run visualizer at https://inferencex.semianalysis.com/inference?unofficialRun=29265000316 |
ichbinblau
force-pushed
the
amd/agentx-v1.0-yanfei
branch
from
12b3333 to
94883e7
Compare
|
see unofficial run visualizer at https://inferencex.semianalysis.com/inference?unofficialRun=29307961980 |
|
see unofficial run visualizer at https://inferencex.semianalysis.com/inference?unofficialRun=29307996568 |
|
see unofficial run visualizer at https://inferencex.semianalysis.com/inference?unofficialRun=29308507513 |
|
see unofficial run visualizer at https://inferencex.semianalysis.com/inference?unofficialRun=29327827754 |
CI already sets KV_OFFLOAD_BACKEND from the workflow; keep the job.slurm and server_sglang metadata forwarding fixes without the redundant recipe logic. Co-authored-by: Cursor <cursoragent@cursor.com>
|
see unofficial run visualizer at https://inferencex.semianalysis.com/inference?unofficialRun=29327827754 |
toJson() pretty-prints with embedded newlines, so the unquoted expansion in
job.slurm's DOCKER_ENV_COMMON was word-split across the docker run command,
corrupting its argument list ("docker: invalid reference format", exit 125).
Quote the value so the whole JSON stays one token.
Co-authored-by: Cursor <cursoragent@cursor.com>
docker run --env-file requires strict single-line KEY=VALUE entries. KV_OFFLOAD_BACKEND_METADATA carries pretty-printed multi-line JSON, which split into invalid env-file lines (e.g. '"name": "hicache",') and aborted the sibling client container launch with "docker: invalid env file ... contains whitespaces". Strip embedded newlines before writing each value so the JSON stays valid but single-line. Co-authored-by: Cursor <cursoragent@cursor.com>
|
see unofficial run visualizer at https://inferencex.semianalysis.com/inference?unofficialRun=29330596598 |
…tripping newlines Naive newline-stripping could silently corrupt a value if a JSON string ever contained a literal embedded newline (merging tokens across the line break). Round-tripping through json.loads/json.dumps guarantees a correct compact single-line representation for client.env, and fails loudly with a clear error if the value isn't valid JSON. Co-authored-by: Cursor <cursoragent@cursor.com>
|
see unofficial run visualizer at https://inferencex.semianalysis.com/inference?unofficialRun=29332974046 |
…ADATA job.slurm always forwards KV_OFFLOAD_BACKEND_METADATA into the server container, even as "" when KV offloading is disabled (the common default case). The prior commit unconditionally ran it through json.loads/json.dumps, which raised JSONDecodeError on that empty string and hard-failed every agentic client-container launch without KV offloading. Only attempt the JSON round-trip when the value is non-empty and not "null", matching how optional_kv_offload_backend_metadata() already treats those as "no metadata" rather than invalid JSON. Co-authored-by: Cursor <cursoragent@cursor.com>
|
see unofficial run visualizer at https://inferencex.semianalysis.com/inference?unofficialRun=29333620847 |
|
see unofficial run visualizer at https://inferencex.semianalysis.com/inference?unofficialRun=29334105829 |
|
see unofficial run visualizer at https://inferencex.semianalysis.com/inference?unofficialRun=29341392884 |
Picks up PR #2191's perf-changelog.yaml entries (dsv4-fp8-h200-vllm, dsv4-fp8-h200-sglang H200 refresh) that were merged to main after this branch diverged. Without this merge, check-changelog's base_ref=main vs head_ref=<this branch> diff sees those entries as "deleted" (present on main, absent here) and fails with "Deletions are not allowed in perf-changelog.yaml", even though this branch never touched them. Co-authored-by: Cursor <cursoragent@cursor.com>
|
see unofficial run visualizer at https://inferencex.semianalysis.com/inference?unofficialRun=29376853679 |
|
/reuse-sweep-run |
|
see unofficial run visualizer at https://inferencex.semianalysis.com/inference?unofficialRun=29392380587 |
|
/reuse-sweep-run 29376853679 |
…nn.py overlay mori_conn.py and the job.slurm auto-apply block it documented were already deleted upstream (retire MoRI conn.py PD-disagg overlay, aca9cee) once the real sglang fix landed in published images. A later unrelated commit (183a987) accidentally recreated this README from scratch while only intending to drop a bullet about a different, already-removed patch (decode_tp_queue_agree.patch), leaving stale docs pointing at a file and job.slurm block that no longer exist. Co-authored-by: Cursor <cursoragent@cursor.com>
|
Thanks for the contribution! Please reach out to respective companies' CODEOWNER to fill in the latest PR_REVIEW_CHECKLIST.md before pinging core maintainer on Slack for review. In order for the signoff PR check bot to trigger, you must follow the PR_REVIEW_CHECKLIST.md template correctly, including the phrase For PR verification, add the PR authors are responsible for ensuring that after merging, all GitHub Action jobs fully pass. A lot of the time, failures are just flakes and simply re-running the failed jobs will fix it. See GitHub's docs on re-running failed jobs 感谢你的贡献！请联系相应公司的 CODEOWNER 填写最新的 PR_REVIEW_CHECKLIST.md，然后再在 Slack 上联系核心维护者进行审阅。为了触发 signoff PR 检查机器人，你必须正确遵循 PR_REVIEW_CHECKLIST.md 模板，包括保留英文语句 如需进行 PR 验证，请为此 PR 添加 PR 作者有责任确保合并后所有 GitHub Action 任务完全通过。 很多时候失败只是偶发抖动（flake），重新运行失败的任务即可解决。参见 GitHub 关于重新运行失败任务的文档 |
8 participants
Summary
Adds end-to-end support for DeepSeek-V4 (DSv4) agentic-coding benchmarks on MI355X in the SGLang disaggregated (prefill/decode) path, plus the multi-node sweep plumbing, result aggregation, and CI fixes needed to make those runs green and ingestible.