|
1 | 1 | {
|
2 | 2 | "versions": {
|
3 |
| - "0.6.4": { |
4 |
| - "imageName": "runpod/worker-v1-vllm:v1.7.0stable-cuda12.1.0", |
| 3 | + "0.6.6": { |
| 4 | + "imageName": "runpod/worker-v1-vllm:v1.8.0stable-cuda12.1.0", |
5 | 5 | "minimumCudaVersion": "12.1",
|
6 | 6 | "categories": [
|
7 | 7 | {
|
|
61 | 61 | }
|
62 | 62 | ]
|
63 | 63 | },
|
64 |
| - "0.6.3": { |
65 |
| - "imageName": "runpod/worker-v1-vllm:v1.6.0stable-cuda12.1.0", |
| 64 | + "0.6.4": { |
| 65 | + "imageName": "runpod/worker-v1-vllm:v1.7.0stable-cuda12.1.0", |
66 | 66 | "minimumCudaVersion": "12.1",
|
67 | 67 | "categories": [
|
68 | 68 | {
|
|
122 | 122 | }
|
123 | 123 | ]
|
124 | 124 | },
|
125 |
| - "0.6.2": { |
126 |
| - "imageName": "runpod/worker-v1-vllm:v1.5.0stable-cuda12.1.0", |
| 125 | + "0.6.3": { |
| 126 | + "imageName": "runpod/worker-v1-vllm:v1.6.0stable-cuda12.1.0", |
127 | 127 | "minimumCudaVersion": "12.1",
|
128 | 128 | "categories": [
|
129 | 129 | {
|
|
134 | 134 | "MAX_MODEL_LEN", "GUIDED_DECODING_BACKEND", "DISTRIBUTED_EXECUTOR_BACKEND",
|
135 | 135 | "WORKER_USE_RAY", "RAY_WORKERS_USE_NSIGHT", "PIPELINE_PARALLEL_SIZE",
|
136 | 136 | "TENSOR_PARALLEL_SIZE", "MAX_PARALLEL_LOADING_WORKERS", "ENABLE_PREFIX_CACHING",
|
137 |
| - "DISABLE_SLIDING_WINDOW", "USE_V2_BLOCK_MANAGER", "NUM_LOOKAHEAD_SLOTS", |
| 137 | + "DISABLE_SLIDING_WINDOW", "NUM_LOOKAHEAD_SLOTS", |
138 | 138 | "SEED", "NUM_GPU_BLOCKS_OVERRIDE", "MAX_NUM_BATCHED_TOKENS", "MAX_NUM_SEQS",
|
139 | 139 | "MAX_LOGPROBS", "DISABLE_LOG_STATS", "QUANTIZATION", "ROPE_SCALING", "ROPE_THETA",
|
140 | 140 | "TOKENIZER_POOL_SIZE", "TOKENIZER_POOL_TYPE", "TOKENIZER_POOL_EXTRA_CONFIG",
|
|
146 | 146 | "NGRAM_PROMPT_LOOKUP_MAX", "NGRAM_PROMPT_LOOKUP_MIN", "SPEC_DECODING_ACCEPTANCE_METHOD",
|
147 | 147 | "TYPICAL_ACCEPTANCE_SAMPLER_POSTERIOR_THRESHOLD", "TYPICAL_ACCEPTANCE_SAMPLER_POSTERIOR_ALPHA",
|
148 | 148 | "MODEL_LOADER_EXTRA_CONFIG", "PREEMPTION_MODE", "PREEMPTION_CHECK_PERIOD",
|
149 |
| - "PREEMPTION_CPU_CAPACITY", "MAX_LOG_LEN", "DISABLE_LOGGING_REQUEST" |
| 149 | + "PREEMPTION_CPU_CAPACITY", "MAX_LOG_LEN", "DISABLE_LOGGING_REQUEST", |
| 150 | + "ENABLE_AUTO_TOOL_CHOICE", "TOOL_CALL_PARSER" |
150 | 151 | ]
|
151 | 152 | },
|
152 | 153 | {
|
|
182 | 183 | }
|
183 | 184 | ]
|
184 | 185 | },
|
185 |
| - "0.6.1": { |
186 |
| - "imageName": "runpod/worker-v1-vllm:v1.4.0stable-cuda12.1.0", |
| 186 | + "0.6.2": { |
| 187 | + "imageName": "runpod/worker-v1-vllm:v1.5.0stable-cuda12.1.0", |
187 | 188 | "minimumCudaVersion": "12.1",
|
188 | 189 | "categories": [
|
189 | 190 | {
|
|
242 | 243 | }
|
243 | 244 | ]
|
244 | 245 | },
|
245 |
| - "0.5.5": { |
246 |
| - "imageName": "runpod/worker-v1-vllm:v1.3.1stable-cuda12.1.0", |
| 246 | + "0.6.1": { |
| 247 | + "imageName": "runpod/worker-v1-vllm:v1.4.0stable-cuda12.1.0", |
247 | 248 | "minimumCudaVersion": "12.1",
|
248 | 249 | "categories": [
|
249 | 250 | {
|
|
0 commit comments