mirror of
https://github.com/NVIDIA/TensorRT-LLM.git
synced 2026-01-14 06:27:45 +08:00
[None][doc] Adding parallelism types in feature combination matrix (#9849)
Signed-off-by: Patrice Castonguay <55748270+pcastonguay@users.noreply.github.com>
This commit is contained in:
parent
b130d58c88
commit
e8cceb06b2
@ -1,19 +1,23 @@
|
|||||||
# Feature Combination Matrix
|
# Feature Combination Matrix
|
||||||
|
|
||||||
| Feature | Overlap Scheduler | CUDA Graph | Attention Data Parallelism | Disaggregated Serving | Chunked Prefill | MTP | EAGLE-3(One Model Engine) | EAGLE-3(Two Model Engine) | Torch Sampler | TLLM C++ Sampler | KV Cache Reuse | Slide Window Attention | Logits Post Processor | Guided Decoding | LoRA |
|
| Feature | Overlap Scheduler | CUDA Graph | Tensor Parallelism | Pipeline Parallelism | Expert Parallelism | Helix Parallelism | Attention Data Parallelism | Disaggregated Serving | Chunked Prefill | MTP | EAGLE-3(One Model Engine) | EAGLE-3(Two Model Engine) | Torch Sampler | TLLM C++ Sampler | KV Cache Reuse | Slide Window Attention | Logits Post Processor | Guided Decoding | LoRA |
|
||||||
| -------------------------- | ----------------- | ---------- | -------------------------- | --------------------- | --------------- | -------- | ------------------------- | ------------------------- | ------------- | ---------------- | -------------- | ---------------------- | --------------------- | --------------- | ---- |
|
| -------------------------- | ----------------- | ---------- | ------------------ | -------------------- | ------------------ | ----------------- | -------------------------- | --------------------- | --------------- | -------- | ------------------------- | ------------------------- | ------------- | ---------------- | -------------- | ---------------------- | --------------------- | --------------- | -------- |
|
||||||
| Overlap Scheduler | --- | | | | | | | | | | | | | | |
|
| Overlap Scheduler | --- | | | | | | | | | | | | | | | | | | |
|
||||||
| CUDA Graph | Yes | --- | | | | | | | | | | | | | |
|
| CUDA Graph | Yes | --- | | | | | | | | | | | | | | | | | |
|
||||||
| Attention Data Parallelism | Yes | Yes | --- | | | | | | | | | | | | |
|
| Tensor Parallelism | Yes | Yes | --- | | | | | | | | | | | | | | | | |
|
||||||
| Disaggregated Serving | Yes | Yes | Yes | --- | | | | | | | | | | | |
|
| Pipeline Parallelism | Yes | Yes | Yes | --- | | | | | | | | | | | | | | | |
|
||||||
| Chunked Prefill | Yes | Yes | Yes | Yes | --- | | | | | | | | | | |
|
| Expert Parallelism | Yes | Yes | Yes | Yes | --- | | | | | | | | | | | | | | |
|
||||||
| MTP | Yes | Yes | Yes | Yes | Yes | --- | | | | | | | | | |
|
| Helix Parallelism | Untested | Yes | Yes | Yes | Yes | --- | | | | | | | | | | | | | |
|
||||||
| EAGLE-3(One Model Engine) | Yes | Yes | Yes | Yes | Yes | No | --- | | | | | | | | |
|
| Attention Data Parallelism | Yes | Yes | Yes | Yes | Yes | Known issues | --- | | | | | | | | | | | | |
|
||||||
| EAGLE-3(Two Model Engine) | Yes | Yes | Yes | Yes | Yes | No | No | --- | | | | | | | |
|
| Disaggregated Serving | Yes | Yes | Yes | Yes | Yes | Yes | Yes | --- | | | | | | | | | | | |
|
||||||
| Torch Sampler | Yes | Yes | Yes | Yes | Yes | Yes | Yes | Yes | --- | | | | | | |
|
| Chunked Prefill | Yes | Yes | Yes | Untested | Yes | Yes | Yes | Yes | --- | | | | | | | | | | |
|
||||||
| TLLM C++ Sampler | Yes | Yes | Yes | Yes | Yes | No | No | No | No | --- | | | | | |
|
| MTP | Yes | Yes | Yes | No | Yes | No | Yes | Yes | Yes | --- | | | | | | | | | |
|
||||||
| KV Cache Reuse | Yes | Yes | Yes | Yes | Yes | Yes | Yes | Yes | Yes | Yes | --- | | | | |
|
| EAGLE-3(One Model Engine) | Yes | Yes | Yes | No | Yes | No | Yes | Yes | Yes | No | --- | | | | | | | | |
|
||||||
| Slide Window Attention | Yes | Yes | Yes | Yes | Yes | Yes | Yes | Yes | Yes | Yes | Yes | --- | | | |
|
| EAGLE-3(Two Model Engine) | Yes | Yes | Yes | No | Yes | No | Yes | Yes | Yes | No | No | --- | | | | | | | |
|
||||||
| Logits Post Processor | Yes | Yes | Yes | No | Yes | No | No | No | Yes | Yes | Yes | Yes | --- | | |
|
| Torch Sampler | Yes | Yes | Yes | Yes | Yes | Yes | Yes | Yes | Yes | Yes | Yes | Yes | --- | | | | | | |
|
||||||
| Guided Decoding | Yes | Yes | Yes | Yes | Yes | Yes | Yes | Yes | Yes | Yes | Yes | Yes | Yes | --- | |
|
| TLLM C++ Sampler | Yes | Yes | Yes | Yes | Yes | Yes | Yes | Yes | Yes | No | No | No | No | --- | | | | | |
|
||||||
| LoRA | Yes | No | Untested | Untested | Untested | Untested | Untested | Untested | Yes | Yes | Yes | Yes | Yes | Untested | --- |
|
| KV Cache Reuse | Yes | Yes | Yes | Yes | Yes | Yes | Yes | Yes | Yes | Yes | Yes | Yes | Yes | Yes | --- | | | | |
|
||||||
|
| Slide Window Attention | Yes | Yes | Yes | Yes | Yes | Untested | Yes | Yes | Yes | Yes | Yes | Yes | Yes | Yes | Yes | --- | | | |
|
||||||
|
| Logits Post Processor | Yes | Yes | Yes | Yes | Yes | Yes | Yes | No | Yes | No | No | No | Yes | Yes | Yes | Yes | --- | | |
|
||||||
|
| Guided Decoding | Yes | Yes | Yes | Yes | Yes | Yes | Yes | Yes | Yes | Yes | Yes | Yes | Yes | Yes | Yes | Yes | Yes | --- | |
|
||||||
|
| LoRA | Yes | No | Yes | Yes | Untested | Untested | Untested | Untested | Yes | Untested | Untested | Untested | Yes | Yes | Yes | Yes | Yes | Untested | --- |
|
||||||
|
|||||||
Loading…
Reference in New Issue
Block a user