Tags

Tags give the ability to mark specific points in history as being important

This project is mirrored from https://github.com/DefTruth/Awesome-LLM-Inference.git. Pull mirroring updated Dec 22, 2024.

v2.6.9

6ad7b307 · 🔥🔥[HADACORE] HADACORE: TENSOR CORE ACCELERATED HADAMARD TRANSFORM KERNEL (#108) · Dec 22, 2024
v2.6.8

32fdb843 · 🔥[BatchLLM] BatchLLM: Optimizing Large Batched LLM Inference with Global... · Dec 08, 2024
v2.6.7

9f548f61 · 🔥[KV Cache Recomputation] Efficient LLM Inference with I/O-Aware Partial KV... · Dec 01, 2024
v2.6.6

40292d73 · 🔥[SparseInfer] SparseInfer: Training-free Prediction of Activation Sparsity... · Nov 25, 2024
v2.6.5

06c76ad3 · 🔥🔥[TP: Comm Compression] Communication Compression for Tensor Parallel LLM Inference (#94) · Nov 18, 2024
v2.6.4

f3f27a73 · 🔥[VL-CACHE] VL-CACHE: SPARSITY AND MODALITY-AWARE KV CACHE COMPRESSION FOR... · Nov 12, 2024
v2.6.3

a854d6cd · 🔥[Tensor Product] Acceleration of Tensor-Product Operations with Tensor Cores (#90) · Oct 31, 2024
v2.6.2

613300d7 · 🔥[FastAttention] FastAttention: Extend FlashAttention2 to NPUs and... · Oct 28, 2024
v2.6.1

7ba03a64 · 🔥[PARALLELSPEC] PARALLELSPEC: PARALLEL DRAFTER FOR EFFICIENT SPECULATIVE DECODING (#84) · Oct 10, 2024
v2.6

c3f14099 · Bump up to v2.6 (#79) · Oct 03, 2024
v2.5

3e436471 · Bump up to v2.5 (#69) · Sep 26, 2024
v2.4

829da5ab · Bump up to v2.4 (#64) · Sep 18, 2024
v2.3

f0860e84 · Bump up to v2.3 (#61) · Sep 09, 2024
v2.2

6d7e9f8a · Bump up to v2.2 (#58) · Sep 04, 2024
v2.1

74f887c1 · Bump up to v2.1 (#50) · Aug 28, 2024
v2.0

8c0b51da · Bump up to v2.0 (#39) · Aug 19, 2024
v1.9

e6b8cf4f · Bump up to v1.9 (#32) · Aug 12, 2024
v1.8

6bb88189 · Bump up to v1.8 (#27) · Aug 05, 2024
v1.7

a6c1528e · Bump up to v1.7 · Jul 29, 2024
v1.6

a1863349 · 🔥🔥[flute] Fast Matrix Multiplications for Lookup Table-Quantized LLMs(@mit.edu etc) · Jul 20, 2024

Prev
1
2
Next