owen/worker-vllm
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

chore(release): v0.9.1

Browse Source 
Signed-off-by: pandyamarut <pandyamarut@gmail.com>
This commit is contained in:
pandyamarut
2025-06-26 11:06:23 -07:00
parent 5ddc2326cd
commit 8839689132
3 changed files with 65 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files
README.md
+3 -3
View File
@@ -18,9 +18,9 @@ Deploy OpenAI-Compatible Blazing-Fast LLM Endpoints powered by the [vLLM](https:
### 1. UI for Deploying vLLM Worker on RunPod console:
![Demo of Deploying vLLM Worker on RunPod console with new UI](media/ui_demo.gif)
### 2. Worker vLLM `v2.6.0` with vLLM `0.9.0` now available under `stable` tags
### 2. Worker vLLM `v2.7.0` with vLLM `0.9.1` now available under `stable` tags
Update v2.6.0 is now available, use the image tag `runpod/worker-v1-vllm:v2.6.0stable-cuda12.1.0`.
Update v2.7.0 is now available, use the image tag `runpod/worker-v1-vllm:v2.7.0stable-cuda12.1.0`.
### 3. OpenAI-Compatible [Embedding Worker](https://github.com/runpod-workers/worker-infinity-embedding) Released
Deploy your own OpenAI-compatible Serverless Endpoint on RunPod with multiple embedding models and fast inference for RAG and more!
@@ -81,7 +81,7 @@ Below is a summary of the available RunPod Worker images, categorized by image s
| CUDA Version | Stable Image Tag | Development Image Tag | Note |
|--------------|-----------------------------------|-----------------------------------|----------------------------------------------------------------------|
| 12.1.0 | `runpod/worker-v1-vllm:v2.6.0stable-cuda12.1.0` | `runpod/worker-v1-vllm:v2.6.0dev-cuda12.1.0` | When creating an Endpoint, select CUDA Version 12.3, 12.2 and 12.1 in the filter. |
| 12.1.0 | `runpod/worker-v1-vllm:v2.7.0stable-cuda12.1.0` | `runpod/worker-v1-vllm:v2.7.0dev-cuda12.1.0` | When creating an Endpoint, select CUDA Version 12.3, 12.2 and 12.1 in the filter. |
docker-bake.hcl
+1 -1
View File
@@ -7,7 +7,7 @@ variable "REPOSITORY" {
}
variable "BASE_IMAGE_VERSION" {
default = "v2.6.0stable"
default = "v2.7.0stable"
}
group "all" {
worker-config.json
+61
View File
@@ -1,5 +1,66 @@
{
"versions": {
"0.9.1": {
"imageName": "runpod/worker-v1-vllm:v2.7.0stable-cuda12.1.0",
"minimumCudaVersion": "12.1",
"categories": [
{
"title": "LLM Settings",
"settings": [
"TOKENIZER", "TOKENIZER_MODE", "SKIP_TOKENIZER_INIT", "TRUST_REMOTE_CODE",
"DOWNLOAD_DIR", "LOAD_FORMAT", "DTYPE", "KV_CACHE_DTYPE", "QUANTIZATION_PARAM_PATH",
"MAX_MODEL_LEN", "GUIDED_DECODING_BACKEND", "DISTRIBUTED_EXECUTOR_BACKEND",
"WORKER_USE_RAY", "RAY_WORKERS_USE_NSIGHT", "PIPELINE_PARALLEL_SIZE",
"TENSOR_PARALLEL_SIZE", "MAX_PARALLEL_LOADING_WORKERS", "ENABLE_PREFIX_CACHING",
"DISABLE_SLIDING_WINDOW", "NUM_LOOKAHEAD_SLOTS",
"SEED", "NUM_GPU_BLOCKS_OVERRIDE", "MAX_NUM_BATCHED_TOKENS", "MAX_NUM_SEQS",
"MAX_LOGPROBS", "DISABLE_LOG_STATS", "QUANTIZATION", "ROPE_SCALING", "ROPE_THETA",
"TOKENIZER_POOL_SIZE", "TOKENIZER_POOL_TYPE", "TOKENIZER_POOL_EXTRA_CONFIG",
"ENABLE_LORA", "MAX_LORAS", "MAX_LORA_RANK", "LORA_EXTRA_VOCAB_SIZE",
"LORA_DTYPE", "LONG_LORA_SCALING_FACTORS", "MAX_CPU_LORAS", "FULLY_SHARDED_LORAS",
"DEVICE", "SCHEDULER_DELAY_FACTOR", "ENABLE_CHUNKED_PREFILL", "SPECULATIVE_MODEL",
"NUM_SPECULATIVE_TOKENS", "SPECULATIVE_DRAFT_TENSOR_PARALLEL_SIZE",
"SPECULATIVE_MAX_MODEL_LEN", "SPECULATIVE_DISABLE_BY_BATCH_SIZE",
"NGRAM_PROMPT_LOOKUP_MAX", "NGRAM_PROMPT_LOOKUP_MIN", "SPEC_DECODING_ACCEPTANCE_METHOD",
"TYPICAL_ACCEPTANCE_SAMPLER_POSTERIOR_THRESHOLD", "TYPICAL_ACCEPTANCE_SAMPLER_POSTERIOR_ALPHA",
"MODEL_LOADER_EXTRA_CONFIG", "PREEMPTION_MODE", "PREEMPTION_CHECK_PERIOD",
"PREEMPTION_CPU_CAPACITY", "MAX_LOG_LEN", "DISABLE_LOGGING_REQUEST",
"ENABLE_AUTO_TOOL_CHOICE", "TOOL_CALL_PARSER"
]
},
{
"title": "Tokenizer Settings",
"settings": [
"TOKENIZER_NAME", "TOKENIZER_REVISION", "CUSTOM_CHAT_TEMPLATE"
]
},
{
"title": "System Settings",
"settings": [
"GPU_MEMORY_UTILIZATION", "MAX_PARALLEL_LOADING_WORKERS", "BLOCK_SIZE",
"SWAP_SPACE", "ENFORCE_EAGER", "MAX_SEQ_LEN_TO_CAPTURE", "DISABLE_CUSTOM_ALL_REDUCE"
]
},
{
"title": "Streaming Settings",
"settings": [
"DEFAULT_BATCH_SIZE", "DEFAULT_MIN_BATCH_SIZE", "DEFAULT_BATCH_SIZE_GROWTH_FACTOR"
]
},
{
"title": "OpenAI Settings",
"settings": [
"RAW_OPENAI_OUTPUT", "OPENAI_RESPONSE_ROLE", "OPENAI_SERVED_MODEL_NAME_OVERRIDE"
]
},
{
"title": "Serverless Settings",
"settings": [
"MAX_CONCURRENCY", "DISABLE_LOG_STATS", "DISABLE_LOG_REQUESTS"
]
}
]
},
"0.9.0": {
"imageName": "runpod/worker-v1-vllm:v2.6.0stable-cuda12.1.0",
"minimumCudaVersion": "12.1",