evo2-nim
Compare original and translation side by side
🇺🇸
Original
English🇨🇳
Translation
ChineseEvo 2 NIM
Evo 2 NIM
Use Evo 2 for DNA generation and, locally, layer-output extraction. Use this
for basic hosted/local use; load supplemental files only when needed:
SKILL.md- : exact schemas, layer names, Docker flags, hardware notes.
references/api.md - : genomic use cases, limits, and interpretation.
references/science.md - : generation/forward parameter effects.
references/parameters.md - : DNA, probability, timing, and tensor checks.
references/validation.md - : compact hosted/local request patterns.
references/examples.md
使用Evo 2进行DNA生成,在本地部署场景下还可提取层输出。本适用于基础的云端/本地使用场景;仅在需要时加载补充文件:
SKILL.md- :精确的模式、层名称、Docker参数、硬件说明。
references/api.md - :基因组学用例、限制条件及解读说明。
references/science.md - :生成/前向传播参数的影响。
references/parameters.md - :DNA、概率、时序及张量检查。
references/validation.md - :简洁的云端/本地请求示例。
references/examples.md
Choose Mode
选择模式
Ask only when context is unclear:
Hosted NVIDIA API or local Docker Evo 2 NIM?
- Hosted generation:
https://health.api.nvidia.com/v1/biology/arc/evo2-40b/generate - Local generation:
http://localhost:8000/biology/arc/evo2/generate - Local forward/layer outputs:
http://localhost:8000/biology/arc/evo2/forward
The hosted docs expose generation. is documented for local Docker;
do not invent a hosted endpoint. Hosted requests use . Supported local Docker
startup uses (or via the preflight) for
registry login, entitlement checks, and first-run model downloads; pass it
into the container with . Local inference requests use no
auth header after readiness. Warm-cache key-free startup varies by
image/version and should not be assumed.
/forward/forwardAuthorization: Bearer $NGC_API_KEYNGC_API_KEYNVIDIA_API_KEY-e NGC_API_KEY仅在上下文不明确时询问:
使用NVIDIA云端API还是本地Docker部署的Evo 2 NIM?
- 云端托管生成:
https://health.api.nvidia.com/v1/biology/arc/evo2-40b/generate - 本地生成:
http://localhost:8000/biology/arc/evo2/generate - 本地前向传播/层输出:
http://localhost:8000/biology/arc/evo2/forward
云端文档仅开放生成功能。接口仅针对本地Docker部署提供文档;请勿虚构云端的端点。云端请求需使用。本地Docker启动需使用(或通过预检流程使用)进行镜像仓库登录、权限验证及首次运行时的模型下载;需通过将其传入容器。本地推理请求在服务就绪后无需认证头。无密钥的预热缓存启动方式因镜像/版本而异,请勿默认该方式可用。
/forward/forwardAuthorization: Bearer $NGC_API_KEYNGC_API_KEYNVIDIA_API_KEY-e NGC_API_KEYLocal Docker Requirements
本地Docker部署要求
Evo 2 local deployment requires FP8-capable GPUs. Do not present A100 as
compatible; A100 can pull the image but fails warmup because FP8 requires
compute capability 8.9 or higher.
- Default 40B: 2x H100 80 GB or 1x H200 141 GB. Use for 2x H100, or
NIM_TEST_GPUS=0,1for one H200.NIM_TEST_GPUS=0 - 7B fallback: set ; supported GPUs include H100, H200, RTX 6000 Ada, and L40S.
NIM_VARIANT=7b - Approximate disk: 110 GB for 40B, 50 GB for 7B.
Use shell env first; source repo-root only if present. Do not invent a
cache default or drop the fallback.
.envNVIDIA_API_KEYbash
set -a
[ -f .env ] && . ./.env
set +a
if [ -z "${NGC_API_KEY:-}" ] && [ -n "${NVIDIA_API_KEY:-}" ]; then
export NGC_API_KEY="$NVIDIA_API_KEY"
fi
: "${NGC_API_KEY:?Set NGC_API_KEY or NVIDIA_API_KEY}"
: "${LOCAL_NIM_CACHE:?Set LOCAL_NIM_CACHE}"
echo "$NGC_API_KEY" | docker login nvcr.io --username '$oauthtoken' --password-stdinEvo 2本地部署需要支持FP8的GPU。请勿将A100列为兼容设备;A100可拉取镜像,但因FP8要求计算能力8.9或更高,会在预热阶段失败。
- 默认40B模型:需要2张H100 80 GB或1张H200 141 GB GPU。使用适配2张H100,或
NIM_TEST_GPUS=0,1适配单张H200。NIM_TEST_GPUS=0 - 7B fallback模型:设置;支持的GPU包括H100、H200、RTX 6000 Ada及L40S。
NIM_VARIANT=7b - 磁盘空间需求:40B模型约110 GB,7B模型约50 GB。
优先使用Shell环境变量;仅当存在仓库根目录的文件时才加载该文件。请勿虚构缓存默认值或忽略的 fallback 机制。
.envNVIDIA_API_KEYbash
set -a
[ -f .env ] && . ./.env
set +a
if [ -z "${NGC_API_KEY:-}" ] && [ -n "${NVIDIA_API_KEY:-}" ]; then
export NGC_API_KEY="$NVIDIA_API_KEY"
fi
: "${NGC_API_KEY:?Set NGC_API_KEY or NVIDIA_API_KEY}"
: "${LOCAL_NIM_CACHE:?Set LOCAL_NIM_CACHE}"
echo "$NGC_API_KEY" | docker login nvcr.io --username '$oauthtoken' --password-stdin40B default: 0,1 for 2x H100; set 0 for a single H200.
40B default: 0,1 for 2x H100; set 0 for a single H200.
export NIM_TEST_GPUS="${NIM_TEST_GPUS:-0,1}"
mkdir -p "${LOCAL_NIM_CACHE}"
chmod 700 "${LOCAL_NIM_CACHE}" # owner-only; if the NIM runs as a different UID, add -u "$(id -u)" to docker run
export NIM_TEST_GPUS="${NIM_TEST_GPUS:-0,1}"
mkdir -p "${LOCAL_NIM_CACHE}"
chmod 700 "${LOCAL_NIM_CACHE}" # owner-only; if the NIM runs as a different UID, add -u "$(id -u)" to docker run
For 7B: export NIM_VARIANT=7b; export NIM_TEST_GPUS="${NIM_TEST_GPUS:-0}"
For 7B: export NIM_VARIANT=7b; export NIM_TEST_GPUS="${NIM_TEST_GPUS:-0}"
docker run --rm -it --name evo2-nim
--runtime=nvidia
--gpus ""device=${NIM_TEST_GPUS}""
-e NGC_API_KEY
-e NIM_VARIANT
-v "${LOCAL_NIM_CACHE}:/opt/nim/.cache"
-p 8000:8000
nvcr.io/nim/arc/evo2:2
--runtime=nvidia
--gpus ""device=${NIM_TEST_GPUS}""
-e NGC_API_KEY
-e NIM_VARIANT
-v "${LOCAL_NIM_CACHE}:/opt/nim/.cache"
-p 8000:8000
nvcr.io/nim/arc/evo2:2
Readiness:
```bash
until curl -sf http://localhost:8000/v1/health/ready; do sleep 10; doneIf RTX PRO 6000 Blackwell Workstation fails with no Transformer Engine
attention backend, treat it as outside the current validated matrix and rerun
on a documented GPU/runtime.
docker run --rm -it --name evo2-nim
--runtime=nvidia
--gpus ""device=${NIM_TEST_GPUS}""
-e NGC_API_KEY
-e NIM_VARIANT
-v "${LOCAL_NIM_CACHE}:/opt/nim/.cache"
-p 8000:8000
nvcr.io/nim/arc/evo2:2
--runtime=nvidia
--gpus ""device=${NIM_TEST_GPUS}""
-e NGC_API_KEY
-e NIM_VARIANT
-v "${LOCAL_NIM_CACHE}:/opt/nim/.cache"
-p 8000:8000
nvcr.io/nim/arc/evo2:2
就绪检查:
```bash
until curl -sf http://localhost:8000/v1/health/ready; do sleep 10; done如果RTX PRO 6000 Blackwell工作站因缺少Transformer Engine注意力后端而运行失败,将其视为超出当前验证矩阵范围,需在已验证的GPU/运行时环境中重新运行。
DNA Generation
DNA生成
Normalize prompts before sending. Use A/C/G/T unless ambiguous bases are a
deliberate modeling choice and clearly reported.
python
import json
import os
from pathlib import Path
import requests
HOSTED = True
def clean_dna(value: str) -> str:
seq = "".join(value.upper().split())
invalid = sorted(set(seq) - set("ACGT"))
if invalid:
raise ValueError(f"Unexpected DNA characters: {''.join(invalid)}")
return seq
prompt = clean_dna("ACTGACTGACTGACTG")
nim_url = os.getenv("EVO2_NIM_URL", "http://localhost:8000")
url = (
"https://health.api.nvidia.com/v1/biology/arc/evo2-40b/generate"
if HOSTED else f"{nim_url}/biology/arc/evo2/generate"
)
headers = {"Content-Type": "application/json"}
if HOSTED:
api_key = os.getenv("NGC_API_KEY")
headers["Authorization"] = f"Bearer {api_key}"
payload = {
"sequence": prompt,
"num_tokens": 64,
"temperature": 0.7,
"top_k": 3,
"top_p": 0.0,
"random_seed": 1,
"enable_sampled_probs": True,
"enable_elapsed_ms_per_token": True,
}
response = requests.post(url, headers=headers, json=payload, timeout=180)
response.raise_for_status()
result = response.json()
seq = result["sequence"]
if sorted(set(seq.upper()) - set("ACGT")):
raise ValueError("Generated sequence contains unexpected non-ACGT bases")
Path("evo2_generation.json").write_text(json.dumps(result, indent=2) + "\n")
Path("evo2_generated.fa").write_text(f">evo2_generated\n{seq}\n")
print(f"Generated {len(seq)} bases in {result.get('elapsed_ms')} ms")Only request when needed; logits can make responses large.
supports development reproducibility, not biological certainty.
enable_logitsrandom_seed发送请求前需标准化提示词。除非明确报告并将模糊碱基作为建模的刻意选择,否则仅使用A/C/G/T碱基。
python
import json
import os
from pathlib import Path
import requests
HOSTED = True
def clean_dna(value: str) -> str:
seq = "".join(value.upper().split())
invalid = sorted(set(seq) - set("ACGT"))
if invalid:
raise ValueError(f"Unexpected DNA characters: {''.join(invalid)}")
return seq
prompt = clean_dna("ACTGACTGACTGACTG")
nim_url = os.getenv("EVO2_NIM_URL", "http://localhost:8000")
url = (
"https://health.api.nvidia.com/v1/biology/arc/evo2-40b/generate"
if HOSTED else f"{nim_url}/biology/arc/evo2/generate"
)
headers = {"Content-Type": "application/json"}
if HOSTED:
api_key = os.getenv("NGC_API_KEY")
headers["Authorization"] = f"Bearer {api_key}"
payload = {
"sequence": prompt,
"num_tokens": 64,
"temperature": 0.7,
"top_k": 3,
"top_p": 0.0,
"random_seed": 1,
"enable_sampled_probs": True,
"enable_elapsed_ms_per_token": True,
}
response = requests.post(url, headers=headers, json=payload, timeout=180)
response.raise_for_status()
result = response.json()
seq = result["sequence"]
if sorted(set(seq.upper()) - set("ACGT")):
raise ValueError("Generated sequence contains unexpected non-ACGT bases")
Path("evo2_generation.json").write_text(json.dumps(result, indent=2) + "\n")
Path("evo2_generated.fa").write_text(f">evo2_generated\n{seq}\n")
print(f"Generated {len(seq)} bases in {result.get('elapsed_ms')} ms")仅在需要时请求;logits会大幅增加响应体积。用于保障开发阶段的可复现性,而非生物层面的确定性。
enable_logitsrandom_seedLocal Forward Pass
本地前向传播
Forward returns base64-encoded NPZ tensors.
python
import base64
import io
import os
import numpy as np
import requests
nim_url = os.getenv("EVO2_NIM_URL", "http://localhost:8000")
payload = {
"sequence": clean_dna("ACTGACTGACTG"),
"output_layers": ["output_layer", "decoder.layers.3.self_attention"],
}
response = requests.post(
f"{nim_url}/biology/arc/evo2/forward",
headers={"Content-Type": "application/json"},
json=payload,
timeout=300,
)
response.raise_for_status()
npz_bytes = base64.b64decode(response.json()["data"])
with open("evo2_forward_outputs.npz", "wb") as handle:
handle.write(npz_bytes)
arrays = np.load(io.BytesIO(npz_bytes), allow_pickle=False)
for name in arrays.files:
arr = arrays[name]
print(name, arr.shape, arr.dtype, bool(np.isfinite(arr).all()), float(arr.mean()))前向传播返回base64编码的NPZ张量。
python
import base64
import io
import os
import numpy as np
import requests
nim_url = os.getenv("EVO2_NIM_URL", "http://localhost:8000")
payload = {
"sequence": clean_dna("ACTGACTGACTG"),
"output_layers": ["output_layer", "decoder.layers.3.self_attention"],
}
response = requests.post(
f"{nim_url}/biology/arc/evo2/forward",
headers={"Content-Type": "application/json"},
json=payload,
timeout=300,
)
response.raise_for_status()
npz_bytes = base64.b64decode(response.json()["data"])
with open("evo2_forward_outputs.npz", "wb") as handle:
handle.write(npz_bytes)
arrays = np.load(io.BytesIO(npz_bytes), allow_pickle=False)
for name in arrays.files:
arr = arrays[name]
print(name, arr.shape, arr.dtype, bool(np.isfinite(arr).all()), float(arr.mean()))Validate And Report
验证与报告
Save request/response JSON, generated FASTA, and a metrics JSON with sequence
length, GC fraction, ambiguous-base fraction, homopolymer length, sampled-prob
checks, and elapsed timing. Treat invalid schema or alphabet as hard failures;
treat extreme GC, low complexity, duplicates, and missing motifs as warnings.
For deeper checks, read .
references/validation.mdKey fields: , , , (0-6),
(0-1), , , ,
and optional .
sequencenum_tokenstemperaturetop_ktop_prandom_seedenable_sampled_probsenable_elapsed_ms_per_tokenenable_logits保存请求/响应JSON、生成的FASTA文件,以及包含序列长度、GC含量、模糊碱基占比、均聚物长度、采样概率检查和耗时统计的指标JSON文件。将无效模式或碱基视为严重错误;将极端GC含量、低复杂度、重复序列及缺失基序视为警告。如需更深入的检查,请阅读。
references/validation.md关键字段:、、、(0-6)、(0-1)、、、,以及可选的。
sequencenum_tokenstemperaturetop_ktop_prandom_seedenable_sampled_probsenable_elapsed_ms_per_tokenenable_logitsTroubleshooting
故障排查
- : hosted key missing/expired or not sent as Bearer token.
401/403 - : wrong field names such as
422instead ofmax_tokens.num_tokens - Local auth confusion: do not send to localhost.
Authorization - Local startup: first run downloads model assets; wait on .
/v1/health/ready - FP8 failure: use hosted, 7B on a supported FP8 GPU, or documented 40B GPUs.
- :云端密钥缺失/过期,或未以Bearer token形式发送。
401/403 - :字段名称错误,例如使用
422而非max_tokens。num_tokens - 本地认证混淆:请勿向localhost发送头。
Authorization - 本地启动:首次运行会下载模型资源;需等待接口返回就绪状态。
/v1/health/ready - FP8失败:使用云端服务、在支持FP8的GPU上运行7B模型,或使用已验证的40B模型兼容GPU。