| commit |
1.00 |
Pass kwargs to the Mamba2 mixer in Nemotron-H, Falcon-H1 and |
|
Commit message contains explicit AI assi |
2026-09-04 |
| commit |
1.00 |
[MiniCPMV4_6] Update test_small_model_vision_generation_batc |
|
Commit message contains explicit AI assi |
2026-09-01 |
| commit |
1.00 |
[VibeVoice] Skip generate export tests (flaky) (#48396) |
|
Commit message contains explicit AI assi |
2026-08-28 |
| commit |
1.00 |
Bump transformers-mlinter to 0.1.5 and clear the new finding |
|
Commit message contains explicit AI assi |
2026-08-28 |
| commit |
1.00 |
[LongcatFlash] Fix test_longcat_generation_cpu: use device_m |
|
Commit message contains explicit AI assi |
2026-08-27 |
| commit |
1.00 |
[ONNX] Skip affected models on torch 2.13 (two dynamo regres |
|
Commit message contains explicit AI assi |
2026-08-27 |
| commit |
1.00 |
Retry get_daily_ci_runs on stale GitHub API cache (#48374) |
|
Commit message contains explicit AI assi |
2026-08-27 |
| commit |
1.00 |
[conftest] Use get_cpu_ram_total_gib for psutil patch (cgrou |
|
Commit message contains explicit AI assi |
2026-08-27 |
| commit |
1.00 |
Fix flaky test_training_gradient_checkpointing for BigBirdPe |
|
Commit message contains explicit AI assi |
2026-08-27 |
| pr |
1.00 |
Add dots3-note Preview model support |
|
PR body explicitly mentions AI collabora |
2026-08-08 |
| pr |
1.00 |
tests: skip the symlinked hub-cache test when symlinks are u |
|
PR body explicitly mentions AI collabora |
2026-09-05 |
| pr |
1.00 |
Feat/laguna quantized checkpoints support |
|
The description explicitly states it was |
2026-08-20 |
| pr |
1.00 |
Fix D-FINE / RT-DETR main loss being computed over the denoi |
|
The PR explicitly says it was generated |
2026-09-04 |
| pr |
1.00 |
:rotating_light: Vision (2d/3d) rotary embeddings |
|
The description explicitly says AI was a |
2026-08-19 |
| pr |
1.00 |
Add Unlimited OCR |
|
PR body explicitly mentions AI collabora |
2026-06-23 |
| pr |
1.00 |
fix(llama): allow explicit head_dim when hidden_size not div |
|
PR body explicitly mentions AI collabora |
2026-05-26 |
| pr |
1.00 |
Support nested FLA kernel imports for fla-core |
|
PR body explicitly mentions AI collabora |
2026-08-22 |
| pr |
1.00 |
Unified multimodal mixin (mrope) |
|
PR body explicitly mentions AI collabora |
2026-08-14 |
| pr |
1.00 |
Fix Jinja block endings in CHAT WITH MODELS' Writing a chat |
|
PR body explicitly mentions AI collabora |
2026-08-14 |
| pr |
1.00 |
fix: apply _rope_type_labels override to validate_rope for G |
|
PR body explicitly mentions AI collabora |
2026-08-31 |
| pr |
1.00 |
Fix CUBLAS internal error during PEFT finetuning in Gemma3N |
|
PR body explicitly mentions AI collabora |
2026-09-01 |
| pr |
0.45 |
docs: add contribution guide for huggingface/transformers |
|
Explicitly automated submission, though |
2026-09-04 |
| pr |
0.28 |
Fix odd head_dim validation for RoPE configurations |
|
Polished explanatory style, but concrete |
2026-09-04 |
| pr |
0.28 |
[i18n-KO] Translate models_timeline to Korean |
|
Polished explanatory prose is somewhat A |
2026-09-02 |
| pr |
0.25 |
Validate hypothesis_template in zero-shot pipelines to preve |
|
Highly polished and structured, though t |
2026-09-04 |
| pr |
0.25 |
Skip symlinked hub-cache test when the platform cannot creat |
|
Polished technical explanation, but conc |
2026-09-04 |
| pr |
0.22 |
Fix Unrecognized image processor error for legacy Qwen3VL im |
|
Polished and highly structured, but incl |
2026-09-04 |
| pr |
0.20 |
Add Fun-ASR-Nano model |
|
Detailed model-specific content is polis |
2026-05-24 |
| pr |
0.20 |
Add a DevLab Dispatch connectivity probe |
|
Polished and explanatory, but grounded i |
2026-09-04 |
| pr |
0.16 |
Add native TR-HASH model support |
|
Polished exhaustive presentation is some |
2026-08-21 |
| pr |
0.10 |
[mLUKE] Un-skip MLukeTokenizerTest |
|
Highly specific measurements and reprodu |
2026-08-22 |
| commit |
0.08 |
Batch Rebalance Data Sampler (#47340) |
|
Detailed technical changelog with implem |
2026-09-01 |
| commit |
0.08 |
Add offload to gradient checkpointing (#48444) |
|
Technical rationale is specific and repo |
2026-09-01 |
| commit |
0.08 |
Ignore a stale best checkpoint recorded in a resumed trainer |
|
Specific failure mode and test results i |
2026-08-26 |
| pr |
0.08 |
feat(hf_argparser): support dict-typed dataclass fields from |
|
Detailed domain-specific changelog lacks |
2026-09-05 |
| pr |
0.08 |
[Umbrella] Continuous batching fixes for training-while-gene |
|
Detailed benchmarks and issue references |
2026-08-25 |
| pr |
0.08 |
Add Ovis2.5 model support |
|
Specific model, issue, and reviewer refe |
2026-07-30 |
| pr |
0.08 |
Expert-parallel token dispatch: each rank trains on its own |
|
Highly technical and benchmark-specific; |
2026-09-04 |
| pr |
0.08 |
Support for MoE in the GGUF integration |
|
Informal phrasing and specific GGUF deta |
2026-09-04 |
| pr |
0.07 |
Fall back to model type for unresolvable image processor nam |
|
Technical fallback behavior is described |
2026-09-05 |
| commit |
0.06 |
Add TP-plan for muse_glimmer and fix dflash for sharded embe |
|
Detailed domain-specific changelog and i |
2026-09-01 |
| pr |
0.06 |
Add WeatherNext 2 weather forecasting model |
|
Detailed domain-specific implementation |
2026-08-10 |
| pr |
0.06 |
Refactor GGUF to speed-up inference |
|
Technical shorthand, typos, and concrete |
2026-08-04 |
| pr |
0.06 |
Fix DynamicCache.reset() leaving the cache in a corrupt, non |
|
Technical reproduction and root-cause an |
2026-09-03 |
| commit |
0.05 |
fix: decode() batch path respects self.clean_up_tokenization |
|
Concise, domain-specific fix description |
2026-09-01 |
| pr |
0.05 |
[GLM 5.3 Flash] Fix NaN gradients in chunked KDA |
|
Highly specific numerical analysis and d |
2026-09-01 |
| pr |
0.05 |
fix(audio): Route the ALM conversion scripts through from_pr |
|
Terse, domain-specific wording and infor |
2026-09-04 |
| pr |
0.05 |
QA: Add noisy comment checker |
|
Concrete checker rules, CI behavior, and |
2026-09-02 |
| pr |
0.05 |
Add LoMa keypoint matching model |
|
Detailed integration scope and repositor |
2026-07-18 |
| pr |
0.05 |
[generation] Encode multimodal data only once |
|
Concise domain-specific wording and mino |
2026-05-05 |
| commit |
0.04 |
Retire test_multi_gpu_data_parallel_forward (#48508) |
|
Clear technical rationale and repository |
2026-09-04 |
| commit |
0.04 |
Fix VoxtralRealtime rejecting non-static cache implementatio |
|
Detailed domain-specific rationale and r |
2026-09-02 |
| commit |
0.04 |
model: Add NVIDIA Canary-1B-v2 to Transformers (#46825) |
|
Iterative review notes, project jargon, |
2026-09-01 |
| commit |
0.04 |
Grounding dino fp16 dtype [backlog] (#48438) |
|
Specific dtype and model references stro |
2026-09-01 |
| pr |
0.04 |
Kimi linear |
|
Very terse, repository-specific wording |
2026-08-24 |
| pr |
0.04 |
Fix LukeTokenizer dropping / on the plain-text path |
|
Concrete bug diagnosis, file references, |
2026-09-05 |
| pr |
0.04 |
[docs] Add a LiteRT page under community integrations |
|
Specific commands, package versions, and |
2026-09-05 |
| pr |
0.04 |
[generate] stop synchronizing the accelerator on every decod |
|
Informal grammar and detailed implementa |
2026-08-14 |
| pr |
0.04 |
Loading: convert transposed and RoPE-permuted weights before |
|
Concise, highly specific bug analysis an |
2026-09-04 |
| pr |
0.04 |
Processing tests [part 2] |
|
Informal wording, typos, and personal co |
2026-08-12 |
| pr |
0.04 |
[Fix] Clean-up ternaries in the DeepSeek family |
|
Contains project-specific details, typos |
2026-09-01 |
| pr |
0.04 |
Add pose estimation keypoint preprocessing to Sapiens2ImageP |
|
Detailed domain-specific implementation |
2026-07-09 |
| pr |
0.04 |
[New Model] Add MiniCPM3 support |
|
Technical model details and rough format |
2026-04-23 |
| pr |
0.04 |
Fix expert parallelism through Trainer |
|
Concrete Trainer failure modes and imple |
2026-08-22 |
| pr |
0.04 |
Fix hybrid-cache get_mask_sizes redirect to prefer full-atte |
|
The cache behavior analysis is highly sp |
2026-09-03 |
| pr |
0.04 |
docs: document DynamicCache API removals in v5 migration gui |
|
Concise, domain-specific migration notes |
2026-09-03 |
| pr |
0.04 |
Honor `shift_labels` in decoder-only LLM/VLM losses |
|
Highly specific code paths and model lis |
2026-09-02 |
| commit |
0.03 |
[generate] stop synchronizing the accelerator on every decod |
|
Highly domain-specific performance discu |
2026-09-04 |
| commit |
0.03 |
Add support for NeuCodec (#47143) |
|
Detailed iterative commit history with h |
2026-09-02 |
| commit |
0.03 |
Allow capturing only necessary hidden_states with capture_ou |
|
Technical changelog with commit trailers |
2026-09-02 |
| commit |
0.03 |
[Fix] Sparse TikToken tokenizers silently fail (#48446) |
|
Contains technical details, shorthand, a |
2026-09-01 |
| commit |
0.03 |
fix qwen4exp-fp8 ple embedding (#48368) |
|
Informal iterative bullets and typos ind |
2026-09-01 |
| commit |
0.03 |
Init the process group with a load-scaled timeout for sharde |
|
Highly specific performance measurements |
2026-09-01 |
| commit |
0.03 |
Keep MXFP4 weights quantized on XPU when use_kernels is set |
|
Concise domain-specific commit message w |
2026-08-26 |
| pr |
0.03 |
Prevent Whisper long-form crashes after Trainer.train() |
|
Concise, technically specific descriptio |
2026-05-12 |
| pr |
0.03 |
Keep user-typed multimodal placeholders literal |
|
Brief domain-specific explanation reads |
2026-09-05 |
| pr |
0.03 |
Fix D2H sync in Qwen VL vision encoder |
|
Specific profiling observations and impl |
2026-08-01 |
| pr |
0.03 |
Fix GPT-NeoX family tokenization when config flags and seria |
|
Highly specific regression analysis and |
2026-09-05 |
| pr |
0.03 |
Warm the page cache before sharded loading (opt-in via `HF_S |
|
Filesystem measurements, cluster details |
2026-08-23 |
| pr |
0.03 |
[Fix] Use dedicated helpers for DeepGEMM and SonicMoE tests |
|
Brief, natural wording with a concrete r |
2026-09-04 |
| pr |
0.03 |
Base import requirements for processors |
|
Informal phrasing, typos, and opinionate |
2026-09-04 |
| pr |
0.03 |
extend some case to xpu as well |
|
Terse, domain-specific wording and infor |
2026-09-03 |
| pr |
0.03 |
Retire test_multi_gpu_data_parallel_forward |
|
Concise technical rationale with specifi |
2026-09-03 |
| pr |
0.03 |
[Model] Add PP-DocLayoutV4 Model Support |
|
Specific architecture details and review |
2026-08-28 |
| pr |
0.03 |
Fall back to config model_type mapping when image_processor_ |
|
Highly specific root-cause analysis and |
2026-09-03 |
| pr |
0.03 |
fix(minimax): repair HF parity reference - map legacy rotary |
|
Uses precise model and RoPE terminology |
2026-09-02 |
| pr |
0.03 |
[Umbrella] Enable FSDP2 + expert parallelism via a 2-D (fsdp |
|
Highly specific experimental results and |
2026-08-22 |
| pr |
0.03 |
Preserve full request history for continuous batching logits |
|
Concrete implementation details and casu |
2026-09-01 |
| pr |
0.03 |
Ignore causal masks a bit earlier for sdpa |
|
Informal wording, concrete performance d |
2026-08-13 |
| pr |
0.03 |
luke fixe |
|
Typos, broken formatting, and highly spe |
2026-08-29 |
| commit |
0.02 |
Kimi linear (#48250) |
|
Terse, typo-filled commit notes strongly |
2026-09-05 |
| commit |
0.02 |
CI: Point test fixtures at hf-internal-testing copies we alr |
|
Specific fixture paths and incremental i |
2026-09-04 |
| commit |
0.02 |
Fix sliding-window mask `layer_idx` in Gemma3/Gemma4 `create |
|
Specific debugging details and regressio |
2026-09-04 |
| commit |
0.02 |
Support nested FLA kernel imports for fla-core (#48221) |
|
Terse, specific technical wording with i |
2026-09-03 |
| commit |
0.02 |
Fix Inkling inputs_embeds and add more tests (#47827) |
|
Terse, domain-specific commit bullets in |
2026-09-03 |
| commit |
0.02 |
Simplify and fix qwen4 tests (#48340) |
|
Short informal commit bullets lack typic |
2026-09-03 |
| commit |
0.02 |
[docs] Partial checkpointing and group_by_length (#48463) |
|
Terse commit summaries with repository-s |
2026-09-02 |
| commit |
0.02 |
[docs] Kernel updates (#48465) |
|
Short, informal commit notes and domain- |
2026-09-02 |
| commit |
0.02 |
[`Kernels`] Enable functions into kernels registry and allow |
|
Terse implementation notes with specific |
2026-09-02 |
| commit |
0.02 |
[`Qwen4 Exp`] Use partial to avoid skipping mask more easily |
|
Brief technical notes with model-specifi |
2026-09-02 |
| commit |
0.02 |
[`DSA`] Fix vanillas SDPA with padding (#48363) |
|
Short informal commits describing specif |
2026-09-02 |
| commit |
0.02 |
Fix rotary embedding regression (#48477) |
|
Terse debugging notes with specific mode |
2026-09-02 |
| commit |
0.02 |
[MTP] Save memory by only capturing the last layer's hidden_ |
|
Terse, domain-specific title and commit- |
2026-09-02 |
| commit |
0.02 |
Support per-layer MTP configuration (#48264) |
|
Short, informal commit messages and spec |
2026-09-02 |
| commit |
0.02 |
[docs] Fix failing audio doctest (#48380) |
|
Terse commit-style wording and specific |
2026-09-01 |
| commit |
0.02 |
[docs] Fix code snippets (#47772) |
|
Brief, informal commit bullets with proj |
2026-09-01 |
| commit |
0.02 |
[fix] inkling: mps + cuda mel spec extraction (#47432) |
|
Terse technical commits and explicit co- |
2026-09-01 |
| commit |
0.02 |
Raise a clear error when a token is both forced and suppress |
|
Terse issue-style wording is characteris |
2026-09-01 |
| commit |
0.02 |
Clarify device placement in pipelines (#47367) |
|
Short, direct title with no AI-style ela |
2026-09-01 |
| pr |
0.02 |
Fix expert-parallel training: NaN gradients and missing grad |
|
Terse, domain-heavy debugging details an |
2026-08-22 |
| pr |
0.02 |
Skip the expert-parallel sentinel masking when expert parall |
|
Concrete performance profiling and imple |
2026-08-21 |
| pr |
0.02 |
Enable FSDP2 + expert parallelism via a 2-D (fsdp, tp) devic |
|
Detailed distributed-training validation |
2026-09-03 |
| pr |
0.02 |
Handle empty FSDP shards in sharded loading: crash and hang |
|
Specific failure ranks, tensor errors, a |
2026-08-23 |
| pr |
0.02 |
Experts implementations: per-row post-expert hook |
|
Concise implementation-focused descripti |
2026-09-05 |
| pr |
0.02 |
[docs] Pipeline parallel inference |
|
Concise, repository-specific description |
2026-09-04 |
| pr |
0.02 |
Fix failing tests for cohere_compass |
|
Very terse description with a specific t |
2026-08-17 |
| pr |
0.02 |
CI: Point test fixtures at hf-internal-testing copies we alr |
|
Minimal, informal summary with no appare |
2026-09-04 |
| pr |
0.02 |
Pass kwargs to the Mamba2 mixer in Nemotron-H, Falcon-H1 and |
|
Specific model and kernel details, tests |
2026-09-02 |
| pr |
0.02 |
Fix sliding-window mask `layer_idx` in Gemma3/Gemma4 `create |
|
Highly specific reproduction data and de |
2026-09-02 |
| pr |
0.02 |
Register activation kernel layers on XPU |
|
Detailed hardware, kernel, and benchmark |
2026-08-10 |
| pr |
0.02 |
[`Qwen 3.5 Moe`] Fix decorators |
|
Extremely terse and informal, with no bo |
2026-08-31 |
| pr |
0.02 |
Infinite loop in dependency search |
|
Short, direct bug-fix description with s |
2026-08-28 |
| pr |
0.02 |
Fix TextToAudioPipeline crash for tokenizer-only models |
|
Concise, technically specific explanatio |
2026-09-03 |
| commit |
0.01 |
Refactor GGUF to speed-up inference (#47779) |
|
Terse, fragmented commit notes and speci |
2026-09-04 |
| commit |
0.01 |
Fix failing tests for cohere_compass (#48005) |
|
Repetitive updates, sign-offs, and expli |
2026-09-04 |
| commit |
0.01 |
[Fix] Use dedicated helpers for DeepGEMM and SonicMoE tests |
|
Extremely terse commit message with no A |
2026-09-04 |
| commit |
0.01 |
fix failed test cases for glm5_next (#48497) |
|
Brief technical updates and repeated dev |
2026-09-04 |
| commit |
0.01 |
vibevoice: fix bug for quant cache (#48487) |
|
Short, informal bug-fix message with a n |
2026-09-04 |
| commit |
0.01 |
Processing tests [part 2] (#47922) |
|
Casual fragments, typos, and self-correc |
2026-09-04 |
| commit |
0.01 |
QA: Add noisy comment checker (#48484) |
|
Concise implementation notes and informa |
2026-09-04 |
| commit |
0.01 |
:rotating_light: Vision (2d/3d) rotary embeddings (#48105) |
|
Chaotic terse commit notes and typos str |
2026-09-04 |
| commit |
0.01 |
add xpu expectations for hunyuan_vl model tests (#48504) |
|
Brief technical change with a standard S |
2026-09-03 |
| commit |
0.01 |
[`Qwen 3.5 Moe`] Fix decorators (#48436) |
|
Very terse commit-style wording, includi |
2026-09-03 |
| commit |
0.01 |
Infinite loop in dependency search (#48393) |
|
Specific bug fix with a normal human co- |
2026-09-03 |
| commit |
0.01 |
Fix some tests by removing the deprecation cycle (#48503) |
|
Terse commit-style summary with specific |
2026-09-03 |
| commit |
0.01 |
Remove deprecation (#48500) |
|
Extremely terse, informal commit message |
2026-09-03 |
| commit |
0.01 |
[AfMoE] Standardize past_key_values argument naming across f |
|
Specific model terminology and issue ref |
2026-09-03 |
| commit |
0.01 |
Fix Pix2StructTextAttention init using hidden_size instead o |
|
Concise, domain-specific fix description |
2026-09-03 |
| commit |
0.01 |
Fix pre patch release utility (#48499) |
|
Terse commit message naming a specific u |
2026-09-03 |
| commit |
0.01 |
Update dev version (#48498) |
|
Brief, informal version-update message. |
2026-09-03 |
| commit |
0.01 |
Warn once when a hub-kernel function falls back to its refer |
|
Technical commit history and co-author t |
2026-09-03 |
| commit |
0.01 |
doc: fix syntax error and typos in VibeVoice documentation ( |
|
Brief title explicitly describing a synt |
2026-09-02 |
| commit |
0.01 |
Remove deprecated mask functions (#48476) |
|
Minimal commit message directly stating |
2026-09-02 |
| commit |
0.01 |
No inherit decorator for NeoMME (#48457) |
|
Extremely terse fix message with a speci |
2026-09-01 |
| commit |
0.01 |
fix: Add DEIMv2 attribution (#48448) |
|
Concise conventional commit naming a spe |
2026-09-01 |
| commit |
0.01 |
Fix MTP generation test regex gate for escaped layer ignore |
|
Short, highly specific test-fix commit m |
2026-09-01 |
| pr |
0.01 |
[CI] Add link checker |
|
Terse casual wording, typo, and smiley s |
2026-08-20 |
| pr |
0.01 |
:rotating_light: Kernels=True ?! |
|
Brief informal title and wording provide |
2026-08-04 |
| pr |
0.01 |
Add MOSS-Transcribe-Diarize model |
|
Minimal title and natural review exchang |
2026-08-28 |
| pr |
0.01 |
Allow nested rope params for tiny models |
|
Minimal description with a direct issue |
2026-08-31 |
| pr |
0.01 |
fix failed test cases for glm5_next |
|
Terse phrasing and casual reviewer reque |
2026-09-03 |
| pr |
0.01 |
vibevoice: fix bug for quant cache |
|
Informal wording and direct reviewer req |
2026-09-02 |
| pr |
0.01 |
docs: fix malformed link to custom models section in CONTRIB |
|
Casual lowercase phrasing and typo are c |
2026-08-15 |
| pr |
0.01 |
add xpu expectations for hunyuan_vl model tests |
|
Informal wording and abbreviated review |
2026-09-03 |
| pr |
0.01 |
Video processors - general maintenance |
|
Very brief, casual wording is strongly c |
2026-08-24 |
| pr |
0.01 |
Fix some tests by removing the deprecation cycle |
|
Informal wording, typos, and emoji-like |
2026-09-03 |
| commit |
0.00 |
Allow nested rope params for tiny models (#48435) |
|
A lone period provides no evidence of AI |
2026-09-04 |
| commit |
0.00 |
[serge] Fix 2 integration tests for model `fsmt` failing wit |
|
— |
2026-09-03 |
| commit |
0.00 |
[serge] Fix 1 integration tests regressed by commit bd950935 |
|
— |
2026-09-02 |
| commit |
0.00 |
[serge] Fix 2 integration tests for model `cwm` failing with |
|
— |
2026-09-01 |
| commit |
0.00 |
[serge] Fix 2 integration tests for model `hyperclovax` fail |
|
— |
2026-08-31 |
| commit |
0.00 |
fix(generation): Enforce the auto-compile cache check for en |
|
— |
2026-08-31 |
| commit |
0.00 |
fix(models): Drop the position-indexed token type lookup in |
|
— |
2026-08-31 |
| commit |
0.00 |
Document image_hidden_states/pixel_values mutual exclusivity |
|
— |
2026-08-31 |
| commit |
0.00 |
Add NeoMME and NeoMME-Retriever (#47992) |
|
— |
2026-08-31 |
| commit |
0.00 |
Re-order a bit for easier navigation (#48434) |
|
— |
2026-08-31 |
| commit |
0.00 |
Deprecated stuff gone (#48367) |
|
— |
2026-08-31 |
| commit |
0.00 |
[serge] Fix 6 integration tests for model `seamless_m4t_v2` |
|
— |
2026-08-31 |
| commit |
0.00 |
[serge] Fix 4 integration tests for model `generation` faili |
|
— |
2026-08-31 |
| commit |
0.00 |
[Docs]: Update GLM 5.3 (#48401) |
|
— |
2026-08-29 |
| commit |
0.00 |
Avoid print to stdout that fails the job `check_failed_tests |
|
— |
2026-08-28 |
| commit |
0.00 |
Fix incorrect tuple return annotations on forward methods re |
|
— |
2026-08-28 |
| commit |
0.00 |
Fix interval merge invariant in _find_disjoint (#47860) |
|
— |
2026-08-28 |
| commit |
0.00 |
skip mtp slow tests for now (#48328) (#48329) |
|
— |
2026-08-28 |
| commit |
0.00 |
Update Tailscale action version in workflow (#48394) |
|
— |
2026-08-28 |
| commit |
0.00 |
fix some failure in xpu (#48252) |
|
— |
2026-08-28 |
| commit |
0.00 |
[Improvement] Make gated delta rule more explicit (#47625) |
|
— |
2026-08-28 |
| commit |
0.00 |
[CB] Fix wrong device scoping (#48370) |
|
— |
2026-08-28 |
| commit |
0.00 |
Raise when a paged attention forward is called with no cache |
|
— |
2026-08-28 |
| commit |
0.00 |
[docs] Pass ContinuousBatchingConfig and sliding window mode |
|
— |
2026-08-28 |
| commit |
0.00 |
fix: flash-attn fallback failing on torch2.13 (#48388) |
|
— |
2026-08-28 |
| commit |
0.00 |
[Qwen3VLMoe] Update `test_small_model_integration_test_batch |
|
— |
2026-08-27 |
| commit |
0.00 |
Fix `safe_open` mmap memory exhaustion on Windows by using ` |
|
— |
2026-08-27 |
| commit |
0.00 |
Fix Zamba2 construction for num_mem_blocks > 1 checkpoints ( |
|
— |
2026-08-27 |
| commit |
0.00 |
Implement VibeVoice (#40546) |
|
— |
2026-08-27 |
| commit |
0.00 |
[Docs] Change 5.3 Flash pos in toc (#48366) |
|
— |
2026-08-27 |
| commit |
0.00 |
Quiet continuous batching at default verbosity (#48314) |
|
— |
2026-08-27 |
| commit |
0.00 |
Wait for the first request in the async continuous batching |
|
— |
2026-08-27 |
| commit |
0.00 |
[CB] Fail faster (#48334) |
|
— |
2026-08-27 |
| pr |
0.00 |
[serge] Fix 2 integration tests for model `seamless_m4t_v2` |
|
— |
2026-09-05 |
| pr |
0.00 |
[serge] Fix 2 integration tests for model `kosmos2` failing |
|
— |
2026-09-05 |
| pr |
0.00 |
[serge] Fix 2 integration tests for model `glm4_moe` failing |
|
— |
2026-09-05 |
| pr |
0.00 |
[serge] Fix 3 integration tests for model `deepseek_vl` fail |
|
— |
2026-09-04 |
| pr |
0.00 |
[serge] Fix 1 integration test for model `qwen3_vl_moe` fail |
|
— |
2026-09-04 |
| pr |
0.00 |
[serge] Fix 4 integration tests for model `blt` failing with |
|
— |
2026-09-04 |
| pr |
0.00 |
[serge] Fix 4 integration tests regressed by commit ce5c8f5e |
|
— |
2026-09-04 |
| pr |
0.00 |
[serge] Fix 2 integration tests for model `minimax` failing |
|
— |
2026-09-03 |
| pr |
0.00 |
Bump the actions group across 1 directory with 13 updates |
|
— |
2026-08-28 |
| pr |
0.00 |
[serge] Fix 2 integration tests for model `fsmt` failing wit |
|
— |
2026-09-02 |
| pr |
0.00 |
Remove deprecation |
|
Empty description provides no evidence o |
2026-09-03 |
