diff --git a/docs/platforms/ascend_npu_support_features.md b/docs/platforms/ascend_npu_support_features.md index 4f2a83a2f..5e32505e2 100644 --- a/docs/platforms/ascend_npu_support_features.md +++ b/docs/platforms/ascend_npu_support_features.md @@ -3,12 +3,13 @@ This section describes the basic functions and features supported by the Ascend NPU.If you encounter issues or have any questions, please [open an issue](https://github.com/sgl-project/sglang/issues). -If you want to know the meaning and usage of each parameter, click [Service Arguments](https://docs.sglang.io/advanced_features/server_arguments.html). +If you want to know the meaning and usage of each parameter, +click [Service Arguments](https://docs.sglang.io/advanced_features/server_arguments.html). ## Model and tokenizer -| Argument | Defaults | Options | A2 | A3 | -|----------------------------------------|----------|---------------------------------------|------------------------------------------|------------------------------------------| +| Argument | Defaults | Options | A2 | A3 | +|----------------------------------------|----------|---------------------------------------|:----------------------------------------:|:----------------------------------------:| | `--model-path`
`--model` | `None` | Type: str | **** | **** | | `--tokenizer-path` | `None` | Type: str | **** | **** | | `--tokenizer-mode` | `auto` | `auto`, `slow` | **** | **** | @@ -20,27 +21,37 @@ If you want to know the meaning and usage of each parameter, click [Service Argu | `--context-length` | `None` | Type: int | **** | **** | | `--is-embedding` | `False` | bool flag (set to enable) | **** | **** | | `--enable-multimodal` | `None` | bool flag (set to enable) | **** | **** | -| `--revision` | `None` | Type: str | **×** | **×** | -| `--model-impl` | `None` | `auto`, `sglang`,
`transformers` | **×** | **** | +| `--revision` | `None` | Type: str | **×** | **×** | +| `--model-impl` | `None` | `auto`, `sglang`,
`transformers` | **** | **** | ## HTTP server -| Argument | Defaults | Options | A2 | A3 | -|------------------------|-------------|--------------------------------|:----------------------------------------:|:----------------------------------------:| -| `--host` | `127.0.0.1` | Type: str | **** | **** | -| `--port` | `30000` | Type: int | **** | **** | -| `--skip-server-warmup` | `False` | bool flag
(set to enable) | **** | **** | -| `--warmups` | `None` | Type: str | **** | **** | -| `--nccl-port` | `None` | Type: int | **** | **** | +| Argument | Defaults | Options | A2 | A3 | +|-------------------------------------------------------------------|-------------|---------------------------------|:----------------------------------------:|:----------------------------------------:| +| `--host` | `127.0.0.1` | Type: str | **** | **** | +| `--port` | `30000` | Type: int | **** | **** | +| `--skip-server-warmup` | `False` | bool flag
(set to enable) | **** | **** | +| `--warmups` | `None` | Type: str | **** | **** | +| `--nccl-port` | `None` | Type: int | **** | **** | +| `--fastapi-root-path` | `None` | Type: int | **×** | **×** | +| `--grpc-mode` | `None` | Type: int | **×** | **×** | +| `--checkpoint-engine-`
`wait-weights-`
`before-ready` | FALSE | bool flag
(set to enable) | **×** | **×** | ## Quantization and data type -| Argument | Defaults | Options | A2 | A3 | -|-----------------------------|----------|-----------------------------------------|:----------------------------------------:|:----------------------------------------:| -| `--dtype` | `auto` | `auto`,
`float16`,
`bfloat16` | **** | **** | -| `--quantization` | `None` | `modelslim` | **** | **** | -| `--quantization-param-path` | `None` | Type: str | **×** | **×** | -| `--kv-cache-dtype` | `auto` | `auto` | **** | **** | +| Argument | Defaults | Options | A2 | A3 | +|-------------------------------------------------|----------|-----------------------------------------|:----------------------------------------:|:----------------------------------------:| +| `--dtype` | `auto` | `auto`,
`float16`,
`bfloat16` | **** | **** | +| `--quantization` | `None` | `modelslim` | **** | **** | +| `--quantization-param-path` | `None` | Type: str | **×** | **×** | +| `--kv-cache-dtype` | `auto` | `auto` | **** | **** | +| `--enable-fp32-lm-head` | FALSE | bool flag
(set to enable) | **×** | **×** | +| `--modelopt-quant` | | | **×** | **×** | +| `--modelopt-checkpoint-`
`restore-path` | | | **×** | **×** | +| `--modelopt-checkpoint-`
`save-path` | | | **×** | **×** | +| `--modelopt-export-path` | | | **×** | **×** | +| `--quantize-and-serve--`
`rl-quant-profile` | | | **×** | **×** | +| `--load-format flash_rl` | | | **×** | **×** | ## Memory and scheduling @@ -62,6 +73,8 @@ If you want to know the meaning and usage of each parameter, click [Service Argu | `--hybrid-kvcache-ratio` | `None` | Optional[float] | **×** | **×** | | `--swa-full-tokens-ratio` | `0.8` | Type: float | **×** | **×** | | `--disable-hybrid-swa-memory` | `False` | bool flag
(set to enable) | **×** | **×** | +| `--abort-on-priority-`
`when-disabled` | `False` | bool flag
(set to enable) | **×** | **×** | +| `--enable-dynamic-chunking` | | | **×** | **×** | ## Runtime options @@ -71,6 +84,7 @@ If you want to know the meaning and usage of each parameter, click [Service Argu | `--tensor-parallel-size`
`--tp-size` | `1` | Type: int | **** | **** | | `--pipeline-parallel-size`
`--pp-size` | `1` | Type: int | **×** | **×** | | `--pp-max-micro-batch-size` | `None` | Type: int | **×** | **×** | +| `--pp-async-batch-depth` | `None` | Type: int | **×** | **×** | | `--stream-interval` | `1` | Type: int | **** | **** | | `--stream-output` | `False` | bool flag (set to enable) | **** | **** | | `--random-seed` | `None` | Type: int | **** | **** | @@ -78,11 +92,11 @@ If you want to know the meaning and usage of each parameter, click [Service Argu | `--constrained-json-`
`disable-any-whitespace` | `False` | bool flag (set to enable) | **×** | **×** | | `--watchdog-timeout` | `300` | Type: float | **** | **** | | `--soft-watchdog-timeout` | `300` | Type: float | **** | **** | -| `--dist-timeout` | `None` | Type: int | **×** | **×** | +| `--dist-timeout` | `None` | Type: int | **** | **** | | `--base-gpu-id` | `0` | Type: int | **** | **** | | `--gpu-id-step` | `1` | Type: int | **** | **** | | `--sleep-on-idle` | `False` | bool flag (set to enable) | **** | **** | -| `--mm-process-config` | `{}` | | **×** | **×** | +| `--custom-sigquit-handler` | `{}` | | **×** | **×** | ## Logging @@ -92,6 +106,7 @@ If you want to know the meaning and usage of each parameter, click [Service Argu | `--log-level-http` | `None` | Type: str | **** | **** | | `--log-requests` | `False` | bool flag
(set to enable) | **** | **** | | `--log-requests-level` | `2` | `0`, `1`, `2`, `3` | **** | **** | +| `--log-requests-format` | text | text, json | **×** | **×** | | `--crash-dump-folder` | `None` | Type: str | **×** | **×** | | `--crash-on-nan` | `False` | Type: str | **×** | **×** | | `--enable-metrics` | `False` | bool flag
(set to enable) | **×** | **×** | @@ -106,11 +121,18 @@ If you want to know the meaning and usage of each parameter, click [Service Argu | `--generation-tokens-buckets` | `None` | List[str] | **×** | **×** | | `--gc-warning-threshold-secs` | `0.0` | Type: float | **×** | **×** | | `--decode-log-interval` | `40` | Type: int | **** | **** | -| `--enable-request-time-`
`stats-logging` | `False` | bool flag
(set to enable) | **×** | **×** | +| `--enable-request-time-`
`stats-logging` | `False` | bool flag
(set to enable) | **** | **** | | `--kv-events-config` | `None` | Type: str | **×** | **×** | | `--enable-trace` | `False` | bool flag
(set to enable) | **×** | **×** | | `--oltp-traces-endpoint` | `localhost:4317` | Type: str | **×** | **×** | +## RequestMetricsExporter configuration + +| Argument | Defaults | Options | A2 | A3 | +|---------------------------------------|----------|---------|:--------------------------------------:|:--------------------------------------:| +| `--export-metrics-to-`
`file` | FALSE | | **×** | **×** | +| `--export-metrics-to-`
`file-dir` | | | **×** | **×** | + ## API related | Argument | Defaults | Options | A2 | A3 | @@ -132,6 +154,7 @@ If you want to know the meaning and usage of each parameter, click [Service Argu |----------------------------------------|---------------|-------------------------------------------------------------|:----------------------------------------:|:----------------------------------------:| | `--data-parallel-size`
`--dp-size` | `1` | Type: int | **** | **** | | `--load-balance-method` | `round_robin` | `round_robin`,
`shortest_queue`,
`minimum_tokens` | **** | **** | +| `--prefill-round-robin-balance` | `False` | bool flag
(set to enable) | **** | **** | ## Multi-node distributed serving @@ -154,12 +177,12 @@ If you want to know the meaning and usage of each parameter, click [Service Argu |--------------------------|----------|-------------------------------------------------------------------------------------------------------------------------------------------------------------|:----------------------------------------:|:----------------------------------------:| | `--enable-lora` | `False` | Bool flag
(set to enable) | **** | **** | | `--max-lora-rank` | `None` | Type: int | **** | **** | -| `--lora-target-modules` | `None` | `q_proj`,
`k_proj`,
`v_proj`,
`o_proj`,
`gate_proj`,
`up_proj`,
`down_proj`,
`qkv_proj`,
`gate_up_proj`,
`all` | **×** | **×** | +| `--lora-target-modules` | `None` | `q_proj`,
`k_proj`,
`v_proj`,
`o_proj`,
`gate_proj`,
`up_proj`,
`down_proj`,
`qkv_proj`,
`gate_up_proj`,
`all` | **** | **** | | `--lora-paths` | `None` | Type: List[str] /
JSON objects | **** | **** | -| `--max-loras-per-batch` | `8` | Type: int | **×** | **×** | -| `--max-loaded-loras` | `None` | Type: int | **×** | **×** | -| `--lora-eviction-policy` | `lru` | `lru`,
`fifo` | **×** | **×** | -| `--lora-backend` | `triton` | `triton`,
`csgmv` | **×** | **×** | +| `--max-loras-per-batch` | `8` | Type: int | **** | **** | +| `--max-loaded-loras` | `None` | Type: int | **** | **** | +| `--lora-eviction-policy` | `lru` | `lru`,
`fifo` | **** | **** | +| `--lora-backend` | `triton` | `triton`,
`csgmv` | **** | **** | | `--max-lora-chunk-size` | `16` | `16`, `32`,
`64`, `128` | **×** | **×** | ## Kernel Backends (Attention, Sampling, Grammar, GEMM) @@ -184,6 +207,7 @@ If you want to know the meaning and usage of each parameter, click [Service Argu | `--speculative-algorithm` | `None` | `EAGLE`,
`EAGLE3`,
`NEXTN`,
`STANDALONE`,
`NGRAM` | **** | **** | | `--speculative-draft-model-path`
`--speculative-draft-model` | `None` | Type: str | **** | **** | | `--speculative-draft-model-`
`revision` | `None` | Type: str | **×** | **×** | +| `--speculative-draft-load-format` | | | **×** | **×** | | `--speculative-num-steps` | `None` | Type: int | **** | **** | | `--speculative-eagle-topk` | `None` | Type: int | **** | **** | | `--speculative-num-draft-tokens` | `None` | Type: int | **** | **** | @@ -193,6 +217,8 @@ If you want to know the meaning and usage of each parameter, click [Service Argu | `--speculative-attention-`
`mode` | `prefill` | `prefill`,
`decode` | **** | **** | | `--speculative-moe-runner-`
`backend` | `None` | | **** | **** | | `--speculative-moe-a2a-`
`backend` | `None` | | **** | **** | +| `--speculative-draft-attention-backend` | | | **** | **** | +| `--speculative-draft-model-quantization` | | | **** | **** | ## Ngram speculative decoding @@ -241,12 +267,6 @@ If you want to know the meaning and usage of each parameter, click [Service Argu | `--mamba-scheduler-strategy` | `auto` | `auto`,
`no_buffer`,
`extra_buffer` | **×** | **×** | | `--mamba-track-interval` | `256` | Type: int | **×** | **×** | -## Args for multi-item scoring - -| Argument | Defaults | Options | A2 | A3 | -|----------------------------------|----------|-----------|:--------------------------------------:|:--------------------------------------:| -| `--multi-item-scoring-delimiter` | `None` | Type: int | **×** | **×** | - ## Hierarchical cache | Argument | Defaults | Options | A2 | A3 | @@ -268,6 +288,17 @@ If you want to know the meaning and usage of each parameter, click [Service Argu |--------------------|----------|--------------------------------|:--------------------------------------:|:--------------------------------------:| | `--enable-lmcache` | `False` | bool flag
(set to enable) | **×** | **×** | +## Ktransformer server args + +| Argument | Defaults | Options | A2 | A3 | +|----------------------------------------------|----------|---------|:--------------------------------------:|:--------------------------------------:| +| `--kt-weight-path` | | | **×** | **×** | +| `--kt-method` | | | **×** | **×** | +| `--kt-cpuinfer` | | | **×** | **×** | +| `--kt-threadpool-count` | | | **×** | **×** | +| `--kt-num-gpu-experts` | | | **×** | **×** | +| `--kt-max-deferred-`
`experts-per-token` | | | **×** | **×** | + ## Double Sparsity | Argument | Defaults | Options | A2 | A3 | @@ -289,6 +320,12 @@ If you want to know the meaning and usage of each parameter, click [Service Argu | `--offload-prefetch-step` | `1` | Type: int | **×** | **×** | | `--offload-mode` | `cpu` | Type: str | **×** | **×** | +## Args for multi-item scoring + +| Argument | Defaults | Options | A2 | A3 | +|----------------------------------|----------|-----------|:--------------------------------------:|:--------------------------------------:| +| `--multi-item-scoring-delimiter` | `None` | Type: int | **×** | **×** | + ## Optimization/debug options | Argument | Defaults | Options | A2 | A3 | @@ -304,6 +341,7 @@ If you want to know the meaning and usage of each parameter, click [Service Argu | `--enable-symm-mem` | `False` | bool flag
(set to enable) | **×** | **×** | | `--disable-flashinfer-`
`cutlass-moe-fp4-allgather` | `False` | bool flag
(set to enable) | **×** | **×** | | `--enable-tokenizer-`
`batch-encode` | `False` | bool flag
(set to enable) | **** | **** | +| `--disable-tokenizer-`
`batch-encode` | `False` | bool flag
(set to enable) | **×** | **×** | | `--disable-outlines-`
`disk-cache` | `False` | bool flag
(set to enable) | **** | **** | | `--disable-custom-`
`all-reduce` | `False` | bool flag
(set to enable) | **×** | **×** | | `--enable-mscclpp` | `False` | bool flag
(set to enable) | **×** | **×** | @@ -319,6 +357,7 @@ If you want to know the meaning and usage of each parameter, click [Service Argu | `--enable-torch-`
`compile-debug-mode` | `False` | bool flag
(set to enable) | **** | **** | | `--enable-piecewise-`
`cuda-graph` | `False` | bool flag
(set to enable) | **×** | **×** | | `--piecewise-cuda-`
`graph-tokens` | `None` | Type: JSON
list | **×** | **×** | +| `--piecewise-cuda-`
`graph-compiler` | `eager` | ["eager", "inductor"] | **×** | **×** | | `--torch-compile-max-bs` | `32` | Type: int | **×** | **×** | | `--piecewise-cuda-`
`graph-max-tokens` | `4096` | Type: int | **×** | **** | | `--torchao-config` | `` | Type: str | **×** | **×** | @@ -331,6 +370,7 @@ If you want to know the meaning and usage of each parameter, click [Service Argu | `--delete-ckpt-`
`after-loading` | `False` | bool flag
(set to enable) | **×** | **×** | | `--enable-memory-saver` | `False` | bool flag
(set to enable) | **×** | **×** | | `--enable-weights-`
`cpu-backup` | `False` | bool flag
(set to enable) | **×** | **×** | +| `--enable-draft-weights-`
`cpu-backup` | `False` | bool flag
(set to enable) | **×** | **×** | | `--allow-auto-truncate` | `False` | bool flag
(set to enable) | **×** | **×** | | `--enable-custom-`
`logit-processor` | `False` | bool flag
(set to enable) | **×** | **×** | | `--flashinfer-mla-`
`disable-ragged` | `False` | bool flag
(set to enable) | **×** | **×** | @@ -339,28 +379,32 @@ If you want to know the meaning and usage of each parameter, click [Service Argu | `--disable-fast-`
`image-processor` | `False` | bool flag
(set to enable) | **×** | **×** | | `--keep-mm-feature-`
`on-device` | `False` | bool flag
(set to enable) | **×** | **×** | | `--enable-return-`
`hidden-states` | `False` | bool flag
(set to enable) | **** | **** | +| `--enable-return-`
`routed-experts` | `False` | bool flag
(set to enable) | **×** | **×** | | `--scheduler-recv-`
`interval` | `1` | Type: int | **×** | **×** | | `--numa-node` | `None` | List[int] | **×** | **×** | +| `--rl-on-policy-target` | `None` | `fsdp` | **×** | **×** | | `--enable-layerwise-`
`nvtx-marker` | `False` | bool flag
(set to enable) | **×** | **×** | | `--enable-attn-tp-`
`input-scattered` | `False` | bool flag
(set to enable) | **×** | **×** | | `--enable-nsa-prefill-`
`context-parallel` | `False` | bool flag
(set to enable) | **×** | **×** | +| `--enable-fused-qk-`
`norm-rope` | | | **×** | **×** | -## Forward hooks - -| Argument | Defaults | Options | A2 | A3 | -|-------------------|----------|-----------------|:--------------------------------------:|:--------------------------------------:| -| `--forward-hooks` | `None` | Type: JSON list | **×** | **×** | - -## Debug tensor dumps +## Dynamic batch tokenizer | Argument | Defaults | Options | A2 | A3 | |--------------------------------------------------|----------|--------------------------------|:----------------------------------------:|:----------------------------------------:| -| `--debug-tensor-dump-`
`input-file` | `None` | Type: str | **×** | **×** | -| `--debug-tensor-dump-`
`inject` | `False` | Type: str | **×** | **×** | | `--enable-dynamic-`
`batch-tokenizer` | `False` | bool flag
(set to enable) | **** | **** | | `--dynamic-batch-`
`tokenizer-batch-size` | `32` | Type: int | **** | **** | | `--dynamic-batch-`
`tokenizer-batch-timeout` | `0.002` | Type: float | **** | **** | +## Debug tensor dumps + +| Argument | Defaults | Options | A2 | A3 | +|--------------------------------------------|----------|-----------|:--------------------------------------:|:--------------------------------------:| +| `--debug-tensor-dump-`
`output-folder` | `None` | Type: str | **×** | **×** | +| `--debug-tensor-dump-`
`layers` | | | **×** | **×** | +| `--debug-tensor-dump-`
`input-file` | `None` | Type: str | **×** | **×** | +| `--debug-tensor-dump-`
`inject` | `False` | Type: str | **×** | **×** | + ## PD disaggregation | Argument | Defaults | Options | A2 | A3 | @@ -373,18 +417,30 @@ If you want to know the meaning and usage of each parameter, click [Service Argu | `--disaggregation-prefill-pp` | `1` | Type: int | **×** | **×** | | `--disaggregation-ib-device` | `None` | Type: str | **×** | **×** | | `--disaggregation-decode-`
`enable-offload-kvcache` | `False` | bool flag
(set to enable) | **×** | **×** | +| `--disaggregation-decode-`
`enable-fake-auto` | `False` | bool flag
(set to enable) | **×** | **×** | | `--num-reserved-decode-tokens` | `512` | Type: int | **** | **** | | `--disaggregation-decode-`
`polling-interval` | `1` | Type: int | **** | **** | +## Encode prefill disaggregation + +| Argument | Defaults | Options | A2 | A3 | +|------------------------------|----------|---------|:--------------------------------------:|:--------------------------------------:| +| `--encoder-only` | | | **×** | **×** | +| `--language-only` | | | **×** | **×** | +| `--encoder-transfer-backend` | | | **×** | **×** | +| `--encoder-urls` | | | **×** | **×** | + ## Custom weight loader -| Argument | Defaults | Options | A2 | A3 | -|---------------------------------------------------------------------|----------|--------------------------------|:----------------------------------------:|------------------------------------------| -| `--custom-weight-loader` | `None` | List[str] | **×** | **×** | -| `--weight-loader-disable-`
`mmap` | `False` | bool flag
(set to enable) | **** | **** | -| `--remote-instance-weight-`
`loader-seed-instance-ip` | `None` | Type: str | **×** | **×** | -| `--remote-instance-weight-`
`loader-seed-instance-service-port` | `None` | Type: int | **×** | **×** | -| `--remote-instance-weight-`
`loader-send-weights-group-ports` | `None` | Type: JSON
list | **×** | **×** | +| Argument | Defaults | Options | A2 | A3 | +|-------------------------------------------------------------------------|----------|--------------------------------|:----------------------------------------:|------------------------------------------| +| `--custom-weight-loader` | `None` | List[str] | **×** | **×** | +| `--weight-loader-disable-`
`mmap` | `False` | bool flag
(set to enable) | **** | **** | +| `--remote-instance-weight-`
`loader-seed-instance-ip` | `None` | Type: str | **×** | **×** | +| `--remote-instance-weight-`
`loader-seed-instance-service-port` | `None` | Type: int | **×** | **×** | +| `--remote-instance-weight-`
`loader-send-weights-group-ports` | `None` | Type: JSON
list | **×** | **×** | +| `--remote-instance-weight-`
`loader-backend` | | | **×** | **×** | +| `--remote-instance-weight-`
`loader-start-seed-via-transfer-engine` | | | **×** | **×** | ## For PD-Multiplexing @@ -394,8 +450,39 @@ If you want to know the meaning and usage of each parameter, click [Service Argu | `--pdmux-config-path` | `None` | Type: str | **×** | **×** | | `--sm-group-num` | `8` | Type: int | **×** | **×** | +## For Multi-Modal + +| Argument | Defaults | Options | A2 | A3 | +|-----------------------------------------------|----------|-------------------|------------------------------------------|------------------------------------------| +| `--mm-max-concurrent-calls` | | | **×** | **×** | +| `--mm-per-request-timeout` | | | **×** | **×** | +| `--enable-broadcast-mm-`
`inputs-process` | | | **×** | **×** | +| `--mm-process-config` | | | **×** | **×** | +| `--mm-enable-dp-encoder` | | | **×** | **×** | +| `--limit-mm-data-per-request` | `None` | Type: JSON / Dict | **** | **** | + +## For checkpoint decryption + +| Argument | Defaults | Options | A2 | A3 | +|---------------------------------|----------|---------|:--------------------------------------:|:--------------------------------------:| +| `--decrypted-config-file` | | | **×** | **×** | +| `--decrypted-draft-config-file` | | | **×** | **×** | +| `--enable-prefix-mm-cache` | | | **×** | **×** | + ## For deterministic inference | Argument | Defaults | Options | A2 | A3 | |-------------------------------------------|----------|--------------------------------|----------------------------------------|----------------------------------------| | `--enable-deterministic-`
`inference` | `False` | bool flag
(set to enable) | **×** | **×** | + +## For registering hooks + +| Argument | Defaults | Options | A2 | A3 | +|-------------------|----------|-----------------|----------------------------------------|----------------------------------------| +| `--forward-hooks` | `None` | Type: JSON list | **×** | **×** | + +## Configuration file support + +| Argument | Defaults | Options | A2 | A3 | +|------------|----------|---------|----------------------------------------|----------------------------------------| +| `--config` | | yaml | **×** | **×** | diff --git a/docs/platforms/ascend_npu_support_models.md b/docs/platforms/ascend_npu_support_models.md index 42ad6aec7..6ba7956c2 100644 --- a/docs/platforms/ascend_npu_support_models.md +++ b/docs/platforms/ascend_npu_support_models.md @@ -9,7 +9,7 @@ You are welcome to enable various models based on your business requirements. | Models | Model Family | A2 Supported | A3 Supported | |-------------------------------------------|--------------------------------|:----------------------------------------:|:----------------------------------------:| | DeepSeek V3/V3.1 | DeepSeek | **** | **** | -| DeepSeek V3.2 | DeepSeek | **×** | **** | +| DeepSeek V3.2 | DeepSeek | **** | **** | | DeepSeek R1 | DeepSeek | **** | **** | | DeepSeek V2 | DeepSeek | **** | **** | | Qwen3 | Qwen | **** | **** | @@ -26,9 +26,9 @@ You are welcome to enable various models based on your business requirements. | microsoft/Phi-4-multimodal-instruct | Phi | **** | **** | | allenai/OLMoE-1B-7B-0924 | OLMoE | **** | **** | | stabilityai/stablelm-2-1_6b | StableLM | **** | **** | -| CohereForAI/c4ai-command-r-v01 | Command-R | **×** | **** | +| CohereForAI/c4ai-command-r-v01 | Command-R | **** | **** | | huihui-ai/grok-2 | Grok | **×** | **** | -| ZhipuAI/chatglm2-6b | ChatGLM | **×** | **** | +| ZhipuAI/chatglm2-6b | ChatGLM | **** | **** | | Shanghai_AI_Laboratory/internlm2-7b | InternLM 2 | **** | **** | | LGAI-EXAONE/EXAONE-3.5-7.8B-Instruct | ExaONE 3 | **** | **** | | xverse/XVERSE-MoE-A36B | XVERSE | **** | **** | @@ -50,45 +50,45 @@ You are welcome to enable various models based on your business requirements. | Models | Model Family (Variants) | A2 Supported | A3 Supported | |-----------------------------------------------|---------------------------|------------------------------------------|:----------------------------------------:| -| Qwen2.5-VL-72B-Instruct-w8a8 | Qwen-VL | **×** | **** | -| Qwen3-VL-30B-A3B-Instruct | Qwen-VL | **×** | **** | -| Qwen3-VL-8B-Instruct | Qwen-VL | **×** | **** | -| Qwen3-VL-4B-Instruct | Qwen-VL | **×** | **** | -| Qwen3-VL-235B-A22B-Instruct | Qwen-VL | **×** | **** | -| deepseek-ai/deepseek-vl2 | DeepSeek-VL2 | **×** | **** | +| Qwen2.5-VL-72B-Instruct-w8a8 | Qwen-VL | **** | **** | +| Qwen3-VL-30B-A3B-Instruct | Qwen-VL | **** | **** | +| Qwen3-VL-8B-Instruct | Qwen-VL | **** | **** | +| Qwen3-VL-4B-Instruct | Qwen-VL | **** | **** | +| Qwen3-VL-235B-A22B-Instruct | Qwen-VL | **** | **** | +| deepseek-ai/deepseek-vl2 | DeepSeek-VL2 | **** | **** | | deepseek-ai/Janus-Pro-7B | Janus-Pro (1B, 7B) | **** | **** | -| openbmb/MiniCPM-V-2_6 | MiniCPM-V / MiniCPM-o | **×** | **** | +| openbmb/MiniCPM-V-2_6 | MiniCPM-V / MiniCPM-o | **** | **** | | google/gemma-3-4b-it | Gemma 3 (Multimodal) | **** | **** | -| mistralai/Mistral-Small-3.1-24B-Instruct-2503 | Mistral-Small-3.1-24B | **×** | **** | -| microsoft/Phi-4-multimodal-instruct | Phi-4-multimodal-instruct | **×** | **** | -| XiaomiMiMo/MiMo-VL-7B-RL | MiMo-VL (7B) | **×** | **** | +| mistralai/Mistral-Small-3.1-24B-Instruct-2503 | Mistral-Small-3.1-24B | **** | **** | +| microsoft/Phi-4-multimodal-instruct | Phi-4-multimodal-instruct | **** | **** | +| XiaomiMiMo/MiMo-VL-7B-RL | MiMo-VL (7B) | **** | **** | | AI-ModelScope/llava-v1.6-34b | LLaVA (v1.5 & v1.6) | **** | **** | | lmms-lab/llava-next-72b | LLaVA-NeXT (8B, 72B) | **** | **** | -| lmms-lab/llava-onevision-qwen2-7b-ov | LLaVA-OneVision | **×** | **** | -| Kimi/Kimi-VL-A3B-Instruct | Kimi-VL (A3B) | **×** | **** | -| ZhipuAI/GLM-4.5V | GLM-4.5V (106B) | **×** | **** | +| lmms-lab/llava-onevision-qwen2-7b-ov | LLaVA-OneVision | **** | **** | +| Kimi/Kimi-VL-A3B-Instruct | Kimi-VL (A3B) | **** | **** | +| ZhipuAI/GLM-4.5V | GLM-4.5V (106B) | **** | **** | | meta-llama/Llama-3.2-11B-Vision-Instruct | Llama 3.2 Vision (11B) | **×** | **×** | ## Embedding Models | Models | Model Family | A2 Supported | A3 Supported | |-------------------------------------------|--------------------------|------------------------------------------|:----------------------------------------:| -| intfloat/e5-mistral-7b-instruct | E5 (Llama/Mistral based) | **×** | **** | -| iic/gte_Qwen2-1.5B-instruct | GTE-Qwen2 | **×** | **** | +| intfloat/e5-mistral-7b-instruct | E5 (Llama/Mistral based) | **** | **** | +| iic/gte_Qwen2-1.5B-instruct | GTE-Qwen2 | **** | **** | | Qwen/Qwen3-Embedding-8B | Qwen3-Embedding | **×** | **×** | -| Alibaba-NLP/gme-Qwen2-VL-2B-Instruct | GME (Multimodal) | **×** | **** | +| Alibaba-NLP/gme-Qwen2-VL-2B-Instruct | GME (Multimodal) | **** | **** | | AI-ModelScope/clip-vit-large-patch14-336 | CLIP | **** | **** | | BAAI/bge-large-en-v1.5 | BGE | **×** | **×** | ## Reward Models -| Models | Model Family | A2 Supported | A3 Supported | -|---------------------------------------------|---------------------------|----------------------------------------|:----------------------------------------:| -| Skywork/Skywork-Reward-Llama-3.1-8B-v0.2 | Llama3.1 Reward | **×** | **** | -| Shanghai_AI_Laboratory/internlm2-7b-reward | InternLM 2 Reward | **×** | **** | -| Qwen/Qwen2.5-Math-RM-72B | Qwen2.5 Reward - Math | **×** | **** | -| jason9693/Qwen2.5-1.5B-apeach | Qwen2.5 Reward - Sequence | **×** | **** | -| Skywork/Skywork-Reward-Gemma-2-27B-v0.2 | Gemma 2-27B Reward | **×** | **×** | +| Models | Model Family | A2 Supported | A3 Supported | +|---------------------------------------------|---------------------------|------------------------------------------|:----------------------------------------:| +| Skywork/Skywork-Reward-Llama-3.1-8B-v0.2 | Llama3.1 Reward | **** | **** | +| Shanghai_AI_Laboratory/internlm2-7b-reward | InternLM 2 Reward | **** | **** | +| Qwen/Qwen2.5-Math-RM-72B | Qwen2.5 Reward - Math | **** | **** | +| jason9693/Qwen2.5-1.5B-apeach | Qwen2.5 Reward - Sequence | **** | **** | +| Skywork/Skywork-Reward-Gemma-2-27B-v0.2 | Gemma 2-27B Reward | **×** | **×** | ## Rerank Models