|
|
@@ -0,0 +1,131 @@
|
|
|
+# DeepSeek-V4.1-Flash — eugr b12x nightly-20260913 (lab `dev/infernal-invocation`), 4x.
|
|
|
+#
|
|
|
+# P1.2 of the 2026-09-18 night: the r37 typo A/B. r37 (09-13, vllmc687594b8a8)
|
|
|
+# garbled DS4.1 text in the morning bisect (A/B/C: flags excluded; D infeasible
|
|
|
+# — engram-off 4x OOMs, the table is part of the weights and only fits in DRAM
|
|
|
+# at 8x). This runs the lab's NEWER published b12x build (09-13 DockerHub, cut
|
|
|
+# from dev/infernal-invocation — newer than r37's 3fb88fdf tree) with the SAME
|
|
|
+# measured r37 contract (GMU 0.88, 512K, DCP1, block 256, B12X attn/linear/moe,
|
|
|
+# K7 greedy/adaptive, engram disk, instanttensor/lazy). Garbled -> the r37
|
|
|
+# garbling is a lab-tree trait (not our build); clean -> r37-specific
|
|
|
+# regression (file the exact bisect with the lab).
|
|
|
+#
|
|
|
+# Image already pulled on dgx1-4 (24.5 GB). Same model/weights/engram staging
|
|
|
+# as the r37 recipe (NAS snapshot + per-node /var/tmp/engram-local hardlinks).
|
|
|
+engine = "vllm"
|
|
|
+name = "DeepSeek-V4.1-Flash (eugr b12x 0913 = lab dev/infernal-invocation, 4x DCP1, DSpark K7)"
|
|
|
+docker_image = "eugr/spark-vllm-b12x:nightly-20260913" # prebuilt (no docker_image_dir)
|
|
|
+model = "deepseek-ai/DeepSeek-V4.1-Flash"
|
|
|
+parent_model = "deepseek-ai/DeepSeek-V4.1-Flash"
|
|
|
+required_nodes = 4
|
|
|
+tensor_parallel_size = 4
|
|
|
+pipeline_parallel_size = 1
|
|
|
+distributed_backend = "mp"
|
|
|
+shm_size = "32gb"
|
|
|
+# Our r27 build dir images ship with ENTRYPOINT [] — set it explicitly.
|
|
|
+entrypoint = ["vllm", "serve"]
|
|
|
+
|
|
|
+args = [
|
|
|
+ "--served-model-name", "dsv41",
|
|
|
+ "--trust-remote-code",
|
|
|
+ "--distributed-executor-backend", "mp",
|
|
|
+ # GB10 startup-gate value (see header); KV pool is engine-computed from
|
|
|
+ # the remainder (no pin — their profile pins nothing either).
|
|
|
+ "--gpu-memory-utilization", "0.88",
|
|
|
+ # 512K context (our floor — their qualified 131K is not usable for us;
|
|
|
+ # the KV pool is engine-computed from the memory budget, unchanged):
|
|
|
+ "--max-model-len", "524288",
|
|
|
+ "--decode-context-parallel-size", "1",
|
|
|
+ "--max-num-seqs", "4",
|
|
|
+ "--max-num-batched-tokens", "4096",
|
|
|
+ "--prefill-compute-share", "0.4",
|
|
|
+ "--block-size", "256",
|
|
|
+ "--enable-chunked-prefill",
|
|
|
+ "--enable-prefix-caching",
|
|
|
+ "--kv-cache-dtype", "fp8",
|
|
|
+ "--attention-backend", "B12X",
|
|
|
+ "--linear-backend", "b12x",
|
|
|
+ "--moe-backend", "b12x",
|
|
|
+ "--compilation-config", """
|
|
|
+'{"cudagraph_mode":"FULL_AND_PIECEWISE"}'""",
|
|
|
+ "--max_cudagraph_capture_size", "128",
|
|
|
+ # Native DSpark K7 — the draft weights live inside the target checkpoint
|
|
|
+ # (no separate draft repo). Greedy draft, standard rejection, adaptive
|
|
|
+ # verification (the lab's r36 qualified trio vs our prod's K5
|
|
|
+ # probabilistic/block).
|
|
|
+ "--speculative-config", """
|
|
|
+'{"method":"dspark","num_speculative_tokens":7,"draft_tensor_parallel_size":4,"attention_backend":"B12X","draft_sample_method":"greedy","rejection_sample_method":"standard","enable_adaptive_verification":true}'""",
|
|
|
+ # Engram: the model's 196B learned ngram lookup storage. disk mode =
|
|
|
+ # io_uring reads of the table rows from the checkpoint dir (bounded
|
|
|
+ # staging; NOT pinned RAM). cpu_offload stays false (no generic CPU
|
|
|
+ # model offload).
|
|
|
+ "--engram-config", """
|
|
|
+'{"cpu_offload":false,"table_memory":"disk"}'""",
|
|
|
+ "--load-format", "instanttensor",
|
|
|
+ "--safetensors-load-strategy", "lazy",
|
|
|
+ "--generation-config", "vllm",
|
|
|
+ "--override-generation-config", """
|
|
|
+'{"temperature":1.0,"top_p":0.95}'""",
|
|
|
+ "--limit-mm-per-prompt", """
|
|
|
+'{"image":2}'""",
|
|
|
+ "--reasoning-parser", "deepseek_v41",
|
|
|
+ "--tool-call-parser", "deepseek_v41",
|
|
|
+ "--enable-auto-tool-choice",
|
|
|
+ "--jit-monitor-mode", "error",
|
|
|
+]
|
|
|
+
|
|
|
+[env]
|
|
|
+
|
|
|
+# Their serve-ds41-jovian.sh runtime env (multi-node-adapted; the launcher
|
|
|
+# injects NCCL_SOCKET_IFNAME/IB_HCA/GID + VLLM_HOST_IP per node).
|
|
|
+# 2026-09-14 (night shift, operator's typo report): the lab tree's runtime
|
|
|
+# LM-head quantization (vocab_parallel_embedding.py) quantizes an unquantized
|
|
|
+# LM head to MXFP8 BY DEFAULT (envs.py: VLLM_MXFP8_LM_HEAD, default "1").
|
|
|
+# The eugr 2026-09-10 nightly (our prod image) has NO such feature and keeps
|
|
|
+# the BF16 head - the coarsened 8-bit vocab-logit layer is the suspected cause
|
|
|
+# of the typo-rate regression (close-token logits distorted). Opting out.
|
|
|
+VLLM_MXFP8_LM_HEAD = "0"
|
|
|
+NCCL_NCHANNELS = "16"
|
|
|
+NCCL_MIN_NCHANNELS = "16"
|
|
|
+NCCL_MAX_NCHANNELS = "16"
|
|
|
+NCCL_BUFFSIZE = "2097152"
|
|
|
+OMP_NUM_THREADS = "8"
|
|
|
+CUDA_DEVICE_MAX_CONNECTIONS = "32"
|
|
|
+# GB10 arch (theirs sm_120a on RTX PRO 6000):
|
|
|
+CUTE_DSL_ARCH = "sm_121a"
|
|
|
+TORCH_CUDA_ARCH_LIST = "12.1a"
|
|
|
+# Their V2 model-runner + AOT compile pipeline (baked in their image env):
|
|
|
+VLLM_USE_V2_MODEL_RUNNER = "1"
|
|
|
+VLLM_USE_AOT_COMPILE = "1"
|
|
|
+VLLM_USE_STANDALONE_COMPILE = "1"
|
|
|
+VLLM_USE_MEGA_AOT_ARTIFACT = "1"
|
|
|
+VLLM_USE_BREAKABLE_CUDAGRAPH = "0"
|
|
|
+VLLM_USE_FLASHINFER_SAMPLER = "1"
|
|
|
+VLLM_WORKER_MULTIPROC_METHOD = "spawn"
|
|
|
+VLLM_EXECUTE_MODEL_TIMEOUT_SECONDS = "900"
|
|
|
+HF_HUB_OFFLINE = "1"
|
|
|
+# Deliberately NOT set: VLLM_ENABLE_PCIE_ALLREDUCE (single-host PCIe in
|
|
|
+# their profile; cross-node on the switch fabric uses the launcher's NCCL),
|
|
|
+# VLLM_HOST_IP (launcher per-node), NCCL_SOCKET_IFNAME (launcher per cluster).
|
|
|
+
|
|
|
+# --- Engram from node-local NVMe, the rest from the shared NAS ---
|
|
|
+# [composed_model] (standard launcher feature) builds a per-node /tmp dir:
|
|
|
+# the whole DSV4.1 snapshot symlinked into the HF cache + the two 101.5 GB
|
|
|
+# Engram table shards (model-00047/00048) HARDLINKED from the pre-existing
|
|
|
+# per-rank sparse copies in /var/tmp/engram-local (48 GB real per node, built
|
|
|
+# for the eugr/aiden lanes — offset-preserving full-size files, only this
|
|
|
+# rank's rows materialized; hardlink = zero extra disk, same fs as /tmp).
|
|
|
+# The r36 io_uring PLE reader then reads this rank's table rows from local
|
|
|
+# NVMe (no NFS); weights stream from the NAS at load time (one-shot, same as
|
|
|
+# prod). Local files run after the repo symlinks and win at the same name.
|
|
|
+[composed_model]
|
|
|
+mount = "/model"
|
|
|
+
|
|
|
+[[composed_model.sources]]
|
|
|
+repo = "deepseek-ai/DeepSeek-V4.1-Flash" # whole snapshot, symlinked into the HF cache
|
|
|
+
|
|
|
+[[composed_model.local_files]] # hardlinks win over the symlinks above
|
|
|
+host = "/var/tmp/engram-local/DeepSeek-V4.1-Flash/model-00047-of-00048.safetensors"
|
|
|
+
|
|
|
+[[composed_model.local_files]]
|
|
|
+host = "/var/tmp/engram-local/DeepSeek-V4.1-Flash/model-00048-of-00048.safetensors"
|
