Combine DeepSeek V4 recipe and tokenizer changes#71
Closed
alec-flowers wants to merge 15 commits intoNVIDIA:sa-submission-q2-2026from
Closed
Combine DeepSeek V4 recipe and tokenizer changes#71alec-flowers wants to merge 15 commits intoNVIDIA:sa-submission-q2-2026from
alec-flowers wants to merge 15 commits intoNVIDIA:sa-submission-q2-2026from
Conversation
|
@alec-flowers FYI we've pushed another round of changes in my branch |
Codecov Report✅ All modified and coverable lines are covered by tests. Additional details and impacted files@@ Coverage Diff @@
## sa-submission-q2-2026 #71 +/- ##
========================================================
Coverage ? 61.41%
========================================================
Files ? 48
Lines ? 4139
Branches ? 0
========================================================
Hits ? 2542
Misses ? 1597
Partials ? 0 ☔ View full report in Codecov by Sentry. 🚀 New features to boost your workflow:
|
4 tasks
3 tasks
Oseltamivir
added a commit
to SemiAnalysisAI/InferenceX
that referenced
this pull request
Apr 24, 2026
PR 1142's first real sweep hit "ModuleNotFoundError: No module named
'vllm.inputs.data'" on all three multinode jobs. Same error as PR 1129
on GB200.
Root cause: ai-dynamo 1.0.1 (installed by NVIDIA/srt-slurm@sa-submission-q2-2026
via `dynamo: { version: 1.0.1 }`) imports vllm.inputs.data.TokensPrompt,
a path removed in the DSV4 vLLM wheel. Dynamo workers crash during
import before any vLLM flag matters.
Fix, mirroring PR 1129:
- launch_h100-dgxc-slurm.sh: override srt-slurm clone URL/ref via
SRT_SLURM_REPO_URL and SRT_SLURM_REF env vars, set to
alec-flowers/srt-slurm@d60e3f1c (head of NVIDIA/srt-slurm#71) for
dynamo-vllm+dsv4. All other frameworks/models keep NVIDIA upstream.
- Recipes: replace `dynamo.version: 1.0.1` with `dynamo.hash:
6a159fedd8e4a1563aa647c31f622aedbf254b5b`. The fork's schema accepts
`hash:` for pinning a specific ai-dynamo/dynamo commit. That commit
has the matching vllm.inputs import path.
- Recipes: adopt DSV4-specific flags PR 1129 proved necessary for
startup: `enforce-eager: true` (prefill only), `enable-sleep-mode: true`,
`no-disable-hybrid-kv-cache-manager: true`, explicit
`kv-transfer-config` (NixlConnector kv_both), env vars
VLLM_SERVER_DEV_MODE=1 and TILELANG_CLEANUP_TEMP_FILES=1.
- Recipes: drop `data-parallel-hybrid-lb` and `async-scheduling` (DSR1
patterns that PR 1129 omitted on DSV4; keep minimal delta from DSV4
H200 single-node).
Kept H100-specific knobs: VLLM_MOE_DP_CHUNK_SIZE=192, deepep_{high_throughput,
low_latency} all2all backends, VLLM_USE_DEEP_GEMM. Skipped GB200-only
flags (NCCL_MNNVL_ENABLE, NCCL_NVLS_ENABLE, VLLM_USE_NCCL_SYMM_MEM).
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
5 tasks
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
4 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.
Summary
custom_tokenizer: "deepseek_v4"use_chat_templatefor those recipes because DeepSeek V4 does not ship a Jinja chat templateValidation
UV_CACHE_DIR="$PWD/.uv-cache" uv run ruff check src/srtctl/benchmarks/scripts/sa-bench/backend_request_func.pyrecipes/vllm/deepseek-v4-pro/8k1k/*.yamlfiles with PyYAML