sglang fa4 - #10
Open
avnermay wants to merge 123 commits into
Open
Conversation
…d sent to draft process
… flashinfer dependency
Sync with post-merge tgl pyproject pins so editable installs that depend on both packages can resolve. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
…eagle_layers properly
…th a mask tensor can be loaded properly
Strips Phoenix V1 support (PhoenixLlamaForCausalLM, use_phoenix config flag, --phoenix CLI flags, PHOENIX_70B paths, use_eagle_or_phoenix abstraction, phoenix-specific activation conditioning branches, mask_tensor loader skip). Preserves all other improvements from avner/sglang-fa4-phnx. The companion branch avner/sglang-fa4-phnx differs from this branch solely by the phoenix code removed here. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Broly Security ScanNote Baseline snapshot is missing for this repo. Broly is running in PR-only fallback mode until the first scheduled baseline completes. This does not block the PR. Note Summary 4 actionable finding(s) in this PR
1 highest-priority actionable rows in the table below (critical/high first, then top medium).
Dismiss false positivesEach dismissable row has a Dismiss key (
Note Re-scan this PR anytime with
|
![github-advanced-security[bot]](https://avatars.githubusercontent.com/in/57789?s=60&v=4){kind=small}
Comment on lines
+138
to
+140
| hits = glob.glob(os.path.join(path, "snapshots", "*", "config.json")) | ||
| assert hits, f"no config.json under {path}" | ||
| path = os.path.dirname(hits[0]) |
| print(f"[{_ts()}] [metrics] All acceptance lengths: {self._acceptance_lengths}", flush=True) | ||
| print(f"[{_ts()}] [metrics] All cache hits: {self._cache_hits}", flush=True) | ||
| print(f"[{_ts()}] [metrics] Logging acceptance lengths and cache hits to: {self._acceptance_rate_log_path}", flush=True) | ||
| with open(self._acceptance_rate_log_path, "w") as f: |
Comment on lines
+135
to
+136
| fused_total = total_new_tokens + batch_size + batch_size * max_blocks | ||
| fused = torch.empty(fused_total, dtype=torch.int64, device=device) |
| PROFILE = os.environ.get("SSD_PROFILE", "0") == "1" | ||
| TRACE = os.environ.get("SSD_PROFILE_TRACE", "0") == "1" | ||
| _TRACE_NAME = os.environ.get("SSD_PROFILE_TRACE_NAME", f"proc_{os.getpid()}") | ||
| _TRACE_OUT = os.environ.get( |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
No description provided.