This PR makes both clients and servers work on macOS. Specifically, it:
- Follows https://github.com/learning-at-home/hivemind/pull/586 to run a macOS-compatible `p2pd` binary (both x86-64 and ARM64 are supported)
- Fixes forking issues and tests on macOS, Python 3.10+
- Introduces basic support for serving model blocks on Apple M1/M2 GPUs (torch.mps)
- Increases max number of open files by default (it's not enough on Linux and is really small on macOS)
- rpc_inference: server will now accept allocation timeout from user, defaults to no timeout
- bugfix: inference timeout is now measured from the moment the request is received
- previously, you would have to wait for your timeout plus the time it takes to sort through the queue (other users' timeout)
- now, you get AllocationFailed if you had to wait for over (timeout) seconds - regardless of other users
- a request for inference with no timeout will now fail instantly if there is not enough memory available
- dtype number of bytes is now correctly determined for int, bool & other types
---------
Co-authored-by: Your Name <you@example.com>
Co-authored-by: Alexander Borzunov <borzunov.alexander@gmail.com>
Co-authored-by: Aleksandr Borzunov <hxrussia@gmail.com>
Before:
```python
Aug 23 23:51:31.394 [INFO] Loaded Maykeye/TinyLLama-v0 block 0, _IncompatibleKeys(missing_keys=[], unexpected_keys=['self_attn.rotary_emb.inv_freq'])
```
After:
```python
Aug 23 23:51:31.394 [INFO] Loaded Maykeye/TinyLLama-v0 block 0
```
Hiding this since the excess keys in Llama-based models are okay since the latest transformers release.
This PR drops custom generation codes and introduces compatibility with `transformers.GenerationMixin` instead. This includes support for more sampling options (`top_p`, `top_k`, `repetition_penalty` requested in #460) and beam search - all that is now identical to running model with transformers locally.
Most features (excluding beam search and other rarely used stuff) are also compatible with resuming existing sessions.
### Breaking changes
If `.generate()` or forward passes are being run inside an `.inference_session()` context, they now use the opened session by default. So, these snippets are now equivalent:
```python
# Using default session
with model.inference_session(max_length=100):
output_ids = model.generate(input_ids, max_new_tokens=3)
# Explicitly specifying a session
with model.inference_session(max_length=100) as sess:
output_ids = model.generate(input_ids, max_new_tokens=3, session=sess)
```
Earlier, the 1st snippet was creating a new session, which is not what most people expected (= such code was most likely to introduce a bug, which is now fixed).
Right now, long inference requests may occupy Runtime for a few seconds without giving it away to process short (most latency-sensitive requests). This PR fixes it by disallowing the merged pool for long requests and prioritizing the short ones.
This PR extends CI to:
1. Test Llama code using [TinyLlama-v0](https://huggingface.co/Maykeye/TinyLLama-v0).
2. Test rebalancing (sets up a situation where the 1st server needs to change its original position).
3. Check if benchmark scripts run (in case someone breaks its code). Note that the benchmark results are meaningless here (since they're measured on a tiny swarm of CPU servers, with low `--n_steps`).
4. Test `petals.cli.run_dht`.
5. Increase swap space and watch free RAM (a common issue is that actions are cancelled without explanation if there's not enough RAM - so it's a useful reminder + debug tool).
6. Fix flapping tests for bloom-560m by increasing tolerance.
Other minor changes: fix `--help` messages to show defaults, fix docs, tune rebalancing constants.
This prohibits passing `--initial_peers` without arguments, since it's likely to be a side-effect from `--initial_peers $INITIAL_PEERS` with the env var not set.
Users should use `--new_swarm` for that, as explained in the private swarm tutorial.
We choose longer servers to minimize the number of hops but leave some randomization to distribute the load. We also exclude servers known to be unreachable.
This PR does not change any functionality. It merely moves stuff around.
List of changes:
handler.py/_rpc_forward became block_methods/rpc_forward
handler.py/_rpc_backward became block_methods/rpc_backward
the math bits of rpc_inference were extracted into block_methods/iterate_rpc_inference
---------
Co-authored-by: Your Name <you@example.com>
Co-authored-by: artek0chumak <artek.chumak@gmail.com>
Co-authored-by: Aleksandr Borzunov <borzunov.alexander@gmail.com>
The message really doesn't tell me much as a user, since I never touched update_period to begin with:
```
Aug 06 09:43:07.287 [WARN] [petals.server.server.run:701] Declaring blocs to DHT takes more than --update_period, consider increasing it
```
Made it better and more informative.
Servers accessible only via relays may introduce issues if they are the only type of servers holding certain blocks. Specifically, a connection to such servers may be unstable or opened after a certain delay.
This PR changes their self-reported throughput, so that the rebalancing algorithm prefers to put directly available servers for hosting each block.
This PR is designed to avoid OOMs when processing long sequences that happen due to the huge attention logits matrices.
Co-authored-by: Alexander Borzunov <borzunov.alexander@gmail.com>
The value is chosen as some safe value below average at https://health.petals.dev/
Note that if a server uses relays, the effective throughput will be further divided by 2 (see #399).
* Hide GeneratorExit in _iterate_inference_steps()
* Update README.md about `--public_name`
* Use .from_pretrained(..., use_auth_token=token) instead of token=token
until it's fully supported across HF libs
* Use default network speed 25 Mbit/s
* Apply relay penalty in max-throughput routing
* Replace RPS with "tokens/sec per block" in logs
* Increase default expiration
Since `petals.ml` DNS record is still unavailable, we're switching everything to https://petals.dev
Co-authored-by: Aleksandr Borzunov <hxrussia@gmail.com>
This PR:
1. **Adds shortest path routing for inference.** We build a graph with client-server and server-server latencies and compute costs, as well as empirically measured overheads. For client-server latencies, we ping possible first and last servers in a sequence in `SequenceManager.update()`. We penalize servers who may not have enough cache for our request. This uses info added to DHT in #355, #356, #358.
2. **Makes a server ping neighboring servers in addition to next ones.** This is to get an opportunity to change the server even before we use all its blocks (e.g., because a neighboring server is faster). This feature is not enabled though, since it increases graph size for N servers to O(N^2) - but we may enable it if needed.
3. **Fixes a `SequenceManager` bug with the first `update()`.** Previously, this update was likely to produce incorrect information and cause to `MissingBlocksErrors` until the next update happens.
Alexander Borzunov
justheuristic
Artem Chumachenko
Vadim Peretokin
Aleksandr Borzunov
Ikko Eltociear Ashimine