From f6fca4705b21d09dc2bc6e2895501a39cd7adc81 Mon Sep 17 00:00:00 2001 From: rock Date: Thu, 5 Nov 2026 09:11:46 +0800 Subject: [PATCH] feat(llm-serving): run coder as fp16 14B across two V100s Replace the GPTQ W4A16 30B-A3B coder with Qwen2.5-Coder-14B-Instruct at fp16 on TP=2. The V100 has FP16 tensor cores and no INT4 ones, so the 4-bit path paid a dequantisation pass on the SM. Profiling showed SM at 98% with the memory controller at 19%, and the batch-1 step cost matched a full-model read. Same harness, 16 streams: ITL 71.5 -> 39.7 ms, 215 -> 287 tok/s. The deployment keeps the candle-vllm name and the app: candle-vllm label, so coder-service.yaml and every client keep working unchanged. --- k8s/apps/llm-serving/coder-14b-fp16.yaml | 102 +++++++++++++++++++++++ k8s/apps/llm-serving/kustomization.yaml | 9 ++ 2 files changed, 111 insertions(+) create mode 100644 k8s/apps/llm-serving/coder-14b-fp16.yaml diff --git a/k8s/apps/llm-serving/coder-14b-fp16.yaml b/k8s/apps/llm-serving/coder-14b-fp16.yaml new file mode 100644 index 0000000..69be1c4 --- /dev/null +++ b/k8s/apps/llm-serving/coder-14b-fp16.yaml @@ -0,0 +1,102 @@ +# Qwen2.5-Coder-14B-Instruct, fp16, tensor-parallel across two V100s. +# +# Why this model and this precision. The previous workload was Qwen3-Coder-30B-A3B +# in GPTQ W4A16 on one V100. Profiling that deployment showed SM utilisation at +# 98% while the memory controller sat at 19%: the V100 has FP16 tensor cores and +# no INT4 ones, so every decode step ran a dequantisation pass on the SM. That is +# a hardware-generation mismatch, not a tunable. Sequence throughput matches the +# arithmetic: at batch 1 the step cost equalled a full-model read (17.6 ms against +# 15 GB / 900 GB/s = 16.7 ms) while the routed experts alone are ~1.5 GB. +# +# Measured on this hardware, same harness, same 16-stream load: +# +# GPTQ W4A16 30B-A3B, TP=1 : ITL 71.5 ms, 215 tok/s aggregate +# fp16 14B, TP=2 : ITL 39.7 ms, 287 tok/s aggregate +# +# The dense model degrades only 1.4x from 1 to 16 streams (27.9 -> 39.7 ms) while +# the MoE degrades 4.1x (17.6 -> 71.5 ms), because a dense model reads its weights +# once per step and amortises across the batch. The MoE pays expert weight traffic +# per sequence. Single-stream latency is the one case where the MoE still wins +# (17.6 ms against 27.9 ms), since it activates ~3B parameters per token. +# +# TP=2 notes that cost time to establish, so they are recorded here: +# - Sharding needs no code change. Every dimension divides by 2: attention heads +# 40 -> 20, KV heads 8 -> 4, intermediate_size 13824 -> 6912, vocab +# 152064 -> 76032. Verify this first for any replacement model. +# - TP=2 on a GPTQ checkpoint is what crashed (CUDA_ERROR_ILLEGAL_ADDRESS in +# forward()) on the previous model. The cause was quantised weight sharding +# and the g_idx guard in src/openai/models/linear.rs, not TP itself. A dense +# fp16 checkpoint has no g_idx, no packed weights and no scales, so it takes +# the plain column/row-parallel path and the crash does not reproduce. +# - These are V100-PCIE cards with no NVLink, so every layer's all-reduce +# crosses PCIe. It shows up in TTFT (275 ms at 1 stream, 1090 ms at 16) +# more than in ITL. +# - KV capacity is 11635 MB per rank, about 59K context tokens. The fp16 +# weights consume the room the KV pool would otherwise use. This is well +# short of the 256K the previous model targeted, and it is the price of +# leaving the dequantisation path. +# +# Weights must be in the PVC as /mnt/models/coder-14b-fp16 (28 GB, 6 shards). +apiVersion: apps/v1 +kind: Deployment +metadata: + name: candle-vllm + namespace: llm-serving + labels: + app.kubernetes.io/part-of: llm-serving + app: candle-vllm +spec: + replicas: 1 + strategy: + # One replica holds both GPUs, so a rolling update would need a second pair. + # Recreate keeps the rollout to a single weights load. + type: Recreate + selector: + matchLabels: + app: candle-vllm + template: + metadata: + labels: + app.kubernetes.io/part-of: llm-serving + app: candle-vllm + spec: + containers: + - name: candle + image: forgejo.riotpiao.com/riotpiao-poimen/candle-vllm:sm70-gptq-slim + command: ["/usr/local/bin/candle-vllm"] + # fp16, not GPTQ, and two ranks, not one. See the header for the + # measurements and the TP=2 findings. + args: + - --w + - /mnt/models/coder-14b-fp16 + - --d + - 0,1 + - --dtype + - f16 + - --p + - "8080" + - --max-num-seqs + - "32" + # 11.6 GB of KV per rank, about 59K context tokens. The fp16 weights + # leave no room for more. + - --kv-fraction + - "0.85" + ports: + - containerPort: 8080 + resources: + limits: + cpu: "8" + memory: 36Gi + nvidia.com/gpu: "2" + requests: + cpu: "4" + memory: 12Gi + nvidia.com/gpu: "2" + volumeMounts: + - name: models + mountPath: /mnt/models + readOnly: true + volumes: + - name: models + persistentVolumeClaim: + claimName: llm-models diff --git a/k8s/apps/llm-serving/kustomization.yaml b/k8s/apps/llm-serving/kustomization.yaml index 0aa63fc..fa86d46 100644 --- a/k8s/apps/llm-serving/kustomization.yaml +++ b/k8s/apps/llm-serving/kustomization.yaml @@ -13,6 +13,15 @@ resources: # clef-flash runs through clef-serve.yaml, not through an SGLang runtime. SGLang needs # v0.5.22+, published only on CUDA 13, and CUDA 13 dropped Volta kernels. The model # instead runs the implementation it ships (joint_schema_model.py) in fp16 on one V100. + # coder-14b-fp16.yaml owns the `candle-vllm` Deployment name and the + # `app: candle-vllm` label that coder-service.yaml selects. It must be the only + # workload with that label, or the Service splits traffic across two models. + # + # fp16 on two V100s, not GPTQ on one: measured 39.7 ms ITL and 287 tok/s at 16 + # streams against 71.5 ms and 215 tok/s for the 4-bit MoE. The V100 has FP16 + # tensor cores and no INT4 ones, so 4-bit pays dequantisation on the SM while + # the memory controller idles at 19%. + - coder-14b-fp16.yaml - clef-serve.yaml # Stable client-facing name for the chat model. poimen-memory points at this Service, # so the vLLM -> candle-vllm handoff is a selector edit here and no client change.